Upload 8 files

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 512,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.0.dev0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1257641deabed059274264134142852f833920489906287f5da639a9d7371ccf
+size 6485383922

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00d0b987e5b4a0bc9e7b015386574646ef094c4db94ab344982d242383a7b3d0
+size 3242672438

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc26885518f63388705ede55e02f473d9229afe6990122e9969f6d4f178da1da
+size 1064

trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.021627794311024986,
+  "eval_steps": 100000000,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 10.7586,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5e-05,
+      "loss": 6.5292,
+      "step": 500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.99998214600225e-05,
+      "loss": 4.7262,
+      "step": 1000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9999285842640105e-05,
+      "loss": 4.1997,
+      "step": 1500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.999839315550315e-05,
+      "loss": 3.8892,
+      "step": 2000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9997143411362066e-05,
+      "loss": 3.6618,
+      "step": 2500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9995536628067196e-05,
+      "loss": 3.5132,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 416130,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 3000,
+  "total_flos": 1.098714710016e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9d0d01338b60b1be222619b79ea3b0ae2fdbdadaf777c837223a484daa9c2b4
+size 4728