Upload 8 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+optimizer.ptrom filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 64,
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": false,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.41.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45a823b3b13b4b9e9a6aafe0472d4fad914f6f7e62545377835609a764415eff
+size 18494040

optimizer.ptrom

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2180c643d0cc5b3fff66227c71ce3682aad53b8ff96a5c1b2e1bcdb8bdbb9ff9
+size 37035002

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

trainer_state.json

@@ -0,0 +1,137 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2507601166034542,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.018807008745259066,
+      "grad_norm": 0.7771628499031067,
+      "learning_rate": 1.9877931524601816e-05,
+      "loss": 10.1462,
+      "num_input_tokens_seen": 19660800,
+      "step": 150
+    },
+    {
+      "epoch": 0.03761401749051813,
+      "grad_norm": 0.841651201248169,
+      "learning_rate": 1.97525187074119e-05,
+      "loss": 9.8974,
+      "num_input_tokens_seen": 39321600,
+      "step": 300
+    },
+    {
+      "epoch": 0.0564210262357772,
+      "grad_norm": 0.7740743160247803,
+      "learning_rate": 1.9627105890221982e-05,
+      "loss": 9.6653,
+      "num_input_tokens_seen": 58982400,
+      "step": 450
+    },
+    {
+      "epoch": 0.07522803498103627,
+      "grad_norm": 0.8001583218574524,
+      "learning_rate": 1.9501693073032066e-05,
+      "loss": 9.4506,
+      "num_input_tokens_seen": 78643200,
+      "step": 600
+    },
+    {
+      "epoch": 0.09403504372629533,
+      "grad_norm": 0.8240243792533875,
+      "learning_rate": 1.937628025584215e-05,
+      "loss": 9.2539,
+      "num_input_tokens_seen": 98304000,
+      "step": 750
+    },
+    {
+      "epoch": 0.1128420524715544,
+      "grad_norm": 0.7667157053947449,
+      "learning_rate": 1.9250867438652233e-05,
+      "loss": 9.0693,
+      "num_input_tokens_seen": 117964800,
+      "step": 900
+    },
+    {
+      "epoch": 0.13164906121681347,
+      "grad_norm": 0.8228150010108948,
+      "learning_rate": 1.9125454621462316e-05,
+      "loss": 8.8967,
+      "num_input_tokens_seen": 137625600,
+      "step": 1050
+    },
+    {
+      "epoch": 0.15045606996207253,
+      "grad_norm": 0.8424794673919678,
+      "learning_rate": 1.9000041804272396e-05,
+      "loss": 8.7364,
+      "num_input_tokens_seen": 157286400,
+      "step": 1200
+    },
+    {
+      "epoch": 0.1692630787073316,
+      "grad_norm": 0.7859320640563965,
+      "learning_rate": 1.8874628987082483e-05,
+      "loss": 8.5903,
+      "num_input_tokens_seen": 176947200,
+      "step": 1350
+    },
+    {
+      "epoch": 0.18807008745259066,
+      "grad_norm": 0.7881995439529419,
+      "learning_rate": 1.8749216169892567e-05,
+      "loss": 8.4497,
+      "num_input_tokens_seen": 196608000,
+      "step": 1500
+    },
+    {
+      "epoch": 0.20687709619784972,
+      "grad_norm": 0.8333655595779419,
+      "learning_rate": 1.8623803352702647e-05,
+      "loss": 8.3184,
+      "num_input_tokens_seen": 216268800,
+      "step": 1650
+    },
+    {
+      "epoch": 0.2256841049431088,
+      "grad_norm": 0.7956089973449707,
+      "learning_rate": 1.849839053551273e-05,
+      "loss": 8.1998,
+      "num_input_tokens_seen": 235929600,
+      "step": 1800
+    },
+    {
+      "epoch": 0.24449111368836787,
+      "grad_norm": 0.8068310022354126,
+      "learning_rate": 1.8372977718322814e-05,
+      "loss": 8.0871,
+      "num_input_tokens_seen": 255590400,
+      "step": 1950
+    }
+  ],
+  "logging_steps": 150,
+  "max_steps": 23925,
+  "num_input_tokens_seen": 262144000,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4047671132160000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cde99b26e6ad0be4341c488ddc29911f5c5e44dd52e53c785a43dc3f89cfc61e
+size 5112