Training in progress, step 4020, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebfe5edf81138c978229a3a68b0fe6644c67b98edc7c5fe61004927e35302f75
+oid sha256:35a69ca220b03dc6504efc110f15929f9ae57c96d280eb843d1af6a4264874a6
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fb53f00fdd7fbcafad95bc9586286b21025aebe6a7a756c6a906a18324316bc
+oid sha256:df293182e1e9c9d15f7f8f232a05259e88feaf1f67100eb23fec82413de6cd98
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43c690d898c7ec435e0a3e95049a4459dd3ca635c017bbe0a97e3303b2d233ca
+oid sha256:0d0bcdc2595dd39333bdd13b49d9cd082e2eb8110dac33ed099c7f11efef73d4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddd4c9ae93fd7d164e48abdd1f7e950a314350432c3244939b41b87291d2074a
+oid sha256:87ec9f1ba3ae289c7a0ef682226dbd37810689a9b5a9a4bec38e00e5e276301e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.32,
+  "epoch": 0.3216,
   "eval_steps": 500,
-  "global_step": 4000,
+  "global_step": 4020,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1407,6 +1407,13 @@
       "learning_rate": 2.778325235483954e-05,
       "loss": 3.5112,
       "step": 4000
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 32.5091667175293,
+      "learning_rate": 2.775776814817928e-05,
+      "loss": 3.4266,
+      "step": 4020
     }
   ],
   "logging_steps": 20,
@@ -1414,7 +1421,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 9444034888728576.0,
+  "total_flos": 9487404305154048.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null