Upload with huggingface_hub

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "JackFram/llama-160m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.28.0.dev0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a822fbdc9b7e882427a56e6b987b1b29d8c3d708d55c59e84843df01ba4eec37
+size 1299404037

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87dcaff3067d333cc04b3cff9b960f3e058f1cdb6c024a8e564296bcbc7265c1
+size 649710859

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc81a4ed07eaae97e601e6dad9894c368270413e9040807580143d45f03df338
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c633ca84a20b37c6163bfda2b956c8311893b200690645206f79af2ceba502a5
+size 623

trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 2414,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00027499999999999996,
+      "loss": 2.2345,
+      "step": 603
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.330522060394287,
+      "eval_runtime": 78.1023,
+      "eval_samples_per_second": 478.232,
+      "eval_steps_per_second": 59.781,
+      "step": 603
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0002499585406301824,
+      "loss": 1.9491,
+      "step": 1207
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.3658900260925293,
+      "eval_runtime": 78.301,
+      "eval_samples_per_second": 477.018,
+      "eval_steps_per_second": 59.629,
+      "step": 1207
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0002249585406301824,
+      "loss": 1.7348,
+      "step": 1810
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.463245391845703,
+      "eval_runtime": 77.97,
+      "eval_samples_per_second": 479.043,
+      "eval_steps_per_second": 59.882,
+      "step": 1810
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00019991708126036484,
+      "loss": 1.5141,
+      "step": 2414
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.605247735977173,
+      "eval_runtime": 77.3626,
+      "eval_samples_per_second": 482.804,
+      "eval_steps_per_second": 60.352,
+      "step": 2414
+    }
+  ],
+  "max_steps": 7236,
+  "num_train_epochs": 12,
+  "total_flos": 9.504695164518605e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:967f68aee10581e1579b84bdb9eefafedd1d17a773f0bc7f85b24bb781128fc3
+size 3567