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:fc7032cbe1c1f7f3892f7d8c6f16f81d0384961efa8c7cdcc75b2aadfe6e2048
+size 1299404037

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:804f88f9f62ea6badb05038cd203fc1cbbcf18760cb09606728715e37c3b0c25
+size 649710859

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ab9b52e364e49a6593a765f851264b1dd5e9b0207961295e70ed4788ef648c
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d542d7af30bf7936e589f2262958b96c9f4208ad02d9568d9bfeb4c17533400f
+size 623

trainer_state.json

@@ -0,0 +1,58 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 2.9998156002212797,
+ "global_step": 4067,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 1.0,
+ "learning_rate": 0.0002875,
+ "loss": 2.3916,
+ "step": 1355
+ },
+ {
+ "epoch": 1.0,
+ "eval_loss": 2.449199914932251,
+ "eval_runtime": 81.8972,
+ "eval_samples_per_second": 456.072,
+ "eval_steps_per_second": 57.01,
+ "step": 1355
+ },
+ {
+ "epoch": 2.0,
+ "learning_rate": 0.00027499077490774905,
+ "loss": 2.193,
+ "step": 2711
+ },
+ {
+ "epoch": 2.0,
+ "eval_loss": 2.462963819503784,
+ "eval_runtime": 81.6595,
+ "eval_samples_per_second": 457.399,
+ "eval_steps_per_second": 57.176,
+ "step": 2711
+ },
+ {
+ "epoch": 3.0,
+ "learning_rate": 0.0002624815498154981,
+ "loss": 2.0534,
+ "step": 4067
+ },
+ {
+ "epoch": 3.0,
+ "eval_loss": 2.501068592071533,
+ "eval_runtime": 80.5824,
+ "eval_samples_per_second": 463.513,
+ "eval_steps_per_second": 57.941,
+ "step": 4067
+ }
+ ],
+ "max_steps": 32520,
+ "num_train_epochs": 24,
+ "total_flos": 1.6618537585823386e+17,
+ "trial_name": null,
+ "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95592390b00ae64ccd8219026cc3ddac8d5cb4389359559f2b130be2570ae91d
+size 3567