step 540

eight_bit_config.json

@@ -1,43 +0,0 @@
-{
-  "_name_or_path": "hivemind/gpt-j-6B-8bit",
-  "activation_function": "gelu_new",
-  "architectures": [
-    "GPTJForCausalLM"
-  ],
-  "attn_pdrop": 0.0,
-  "bos_token_id": 50256,
-  "eight_bit": true,
-  "embd_pdrop": 0.0,
-  "eos_token_id": 50256,
-  "gradient_checkpointing": false,
-  "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gptj",
-  "n_embd": 4096,
-  "n_head": 16,
-  "n_inner": null,
-  "n_layer": 28,
-  "n_positions": 2048,
-  "resid_pdrop": 0.0,
-  "rotary": true,
-  "rotary_dim": 64,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50,
-      "temperature": 1.0
-    }
-  },
-  "tie_word_embeddings": false,
-  "tokenizer_class": "GPT2Tokenizer",
-  "torch_dtype": "float32",
-  "transformers_version": "4.25.1",
-  "use_cache": true,
-  "vocab_size": 50400
-}

eight_bit_fully_trained.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3ec9e447dcae0d53bdde910dfc9e9e2523c4dd69e95088cbca51e74e84dca68a
-size 6316560184

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:776f348ae750a40c43367e039333caef551872f031a95a5bfc92ce2e5e2dafdb
+oid sha256:b2c13d1f6aca9d6c804c0bc9298ed055733e600a46b1bdca00020324eba63c6a
 size 24673403925

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.033567287152883735,
-  "global_step": 440,
+  "epoch": 0.0411962160512664,
+  "global_step": 540,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -182,11 +182,57 @@
       "eval_samples_per_second": 3.319,
       "eval_steps_per_second": 0.424,
       "step": 440
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 2.2626798152923584,
+      "eval_runtime": 94.7992,
+      "eval_samples_per_second": 3.302,
+      "eval_steps_per_second": 0.422,
+      "step": 460
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 2.2764577865600586,
+      "eval_runtime": 95.9001,
+      "eval_samples_per_second": 3.264,
+      "eval_steps_per_second": 0.417,
+      "step": 480
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5e-05,
+      "loss": 2.1752,
+      "step": 500
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 2.270517110824585,
+      "eval_runtime": 95.5609,
+      "eval_samples_per_second": 3.275,
+      "eval_steps_per_second": 0.419,
+      "step": 500
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 2.2533695697784424,
+      "eval_runtime": 95.989,
+      "eval_samples_per_second": 3.261,
+      "eval_steps_per_second": 0.417,
+      "step": 520
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 2.2560901641845703,
+      "eval_runtime": 95.7778,
+      "eval_samples_per_second": 3.268,
+      "eval_steps_per_second": 0.418,
+      "step": 540
     }
   ],
   "max_steps": 13108,
   "num_train_epochs": 1,
-  "total_flos": 6059125112832.0,
+  "total_flos": 7509129560064.0,
   "trial_name": null,
   "trial_params": null
 }