Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15df8bb7b0d650ace01d49121a6ff2801e53098ae1fbd955ed4336f0f8e11ee6
+oid sha256:de0a235f3533624d434eb2d4d1fc3cb99011c3c8700866ddf368ac7140d739a8
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44804d51d5f6b390f04a3c04221e0560893966402950edc2362e929c63a832a3
+oid sha256:8381471a40e6579f72ce5916fb91b4c9d44dc18b662e96d8ec470ca08ac11f3f
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42ae668d05ab3aad6ce208eabfc49a053f98a880118709786e12d55282ae6b22
+oid sha256:e60fc8f32eff402dbfdf1f21a411fe615eb6cdc026d0f67f4f85662b0ad8390e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b474e3bac276f26ded4a53adf20938b4253ff5f990814d1b36777f7eb9de45a
+oid sha256:13c6fd8dd9ac5f94a3fddc347a180544a422ef0ac785334b57fd9dde62a57e91
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008923956733683103,
+  "epoch": 0.001041128285596362,
   "eval_steps": 2000,
-  "global_step": 1200,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,6 +49,13 @@
       "learning_rate": 1.9999998448916044e-05,
       "loss": 1.6922,
       "step": 1200
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 3.6168997287750244,
+      "learning_rate": 1.9999997884752155e-05,
+      "loss": 1.6211,
+      "step": 1400
     }
   ],
   "logging_steps": 200,
@@ -56,7 +63,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 1.5519816481284096e+16,
+  "total_flos": 1.8055337626484736e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null