Training in progress, step 80, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "TitanML/tiny-mixtral",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3584,
+  "max_position_embeddings": 131072,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.48.1"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55c29b985fa1cc18b56f46733fd17a718d9f1690457d49a95bf9bec674c4578
+size 493963120

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7103f530aba0fb0ef51b64ec9539a60845b28b1c16ad8188b2f93e1ffd1309c
+size 501746490

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9906b173df03663b222bd12a0e83af5aaa020a12d4ad3b4f49197437057c696b
+size 15984

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7bf7c9d7fc97693b96ee7a514a4d88728c8624bc298bf36b68fd64703b6ce38
+size 15984

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cba90fd12df41e2a3afe0aa9bdbcb01ea64e70a37cf6d3f1b6f819528d9eedb2
+size 15984

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f677ceac78336a23596ad2dfff49115dd4f2798e6c718f3d9a417036aecc78d
+size 15984

last-checkpoint/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b66cb249efdcbeae07a93ab18308b0dad6ab1938b8cda1783930dd7ca16e400
+size 15984

last-checkpoint/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a32fc5b45250ceb9579d6cdb22a9de146f720394a5fb1a94da8455a621d02420
+size 15984

last-checkpoint/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdaa72ece53788894cbf7d690659103118093c50cbe7ebcc4ad29ce77864063c
+size 15984

last-checkpoint/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e1077a981f60bb0c73ac0edeec6a361fda9845f8d5236c4bc77fda2663cf80d
+size 15984

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fce9536ff5f950cceb3fa69a1e2f266b5d6de86d1ea82239294fb327d0664db
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '### Instruction: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ '### Response: ' + message['content'] + eos_token}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.09467455621301775,
+  "eval_steps": 20,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001183431952662722,
+      "eval_loss": 10.566378593444824,
+      "eval_runtime": 2.0211,
+      "eval_samples_per_second": 743.163,
+      "eval_steps_per_second": 46.51,
+      "step": 1
+    },
+    {
+      "epoch": 0.011834319526627219,
+      "grad_norm": 6.454888820648193,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 10.5688,
+      "step": 10
+    },
+    {
+      "epoch": 0.023668639053254437,
+      "grad_norm": 4.221368789672852,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 10.5293,
+      "step": 20
+    },
+    {
+      "epoch": 0.023668639053254437,
+      "eval_loss": 10.471421241760254,
+      "eval_runtime": 2.0335,
+      "eval_samples_per_second": 738.623,
+      "eval_steps_per_second": 46.225,
+      "step": 20
+    },
+    {
+      "epoch": 0.03550295857988166,
+      "grad_norm": 7.107753753662109,
+      "learning_rate": 4.8e-05,
+      "loss": 10.3814,
+      "step": 30
+    },
+    {
+      "epoch": 0.047337278106508875,
+      "grad_norm": 4.7665696144104,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 9.9244,
+      "step": 40
+    },
+    {
+      "epoch": 0.047337278106508875,
+      "eval_loss": 9.445327758789062,
+      "eval_runtime": 2.0204,
+      "eval_samples_per_second": 743.435,
+      "eval_steps_per_second": 46.527,
+      "step": 40
+    },
+    {
+      "epoch": 0.05917159763313609,
+      "grad_norm": 5.4297027587890625,
+      "learning_rate": 8e-05,
+      "loss": 8.9648,
+      "step": 50
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "grad_norm": 2.0724003314971924,
+      "learning_rate": 9.6e-05,
+      "loss": 8.2558,
+      "step": 60
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "eval_loss": 7.835418224334717,
+      "eval_runtime": 6.0797,
+      "eval_samples_per_second": 247.052,
+      "eval_steps_per_second": 15.461,
+      "step": 60
+    },
+    {
+      "epoch": 0.08284023668639054,
+      "grad_norm": 1.815529227256775,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 7.658,
+      "step": 70
+    },
+    {
+      "epoch": 0.09467455621301775,
+      "grad_norm": 2.478553295135498,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 7.4762,
+      "step": 80
+    },
+    {
+      "epoch": 0.09467455621301775,
+      "eval_loss": 7.448663711547852,
+      "eval_runtime": 2.0159,
+      "eval_samples_per_second": 745.071,
+      "eval_steps_per_second": 46.629,
+      "step": 80
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 40,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3374230997565440.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bed78fd5996b9487484b47ba579fb5de2f0cc969aa32dc5681ad0a64670cef49
+size 6712