Training in progress, step 3000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:724b47d9c8653ca30a08e92b5b2db184a6a2691e07d099d47dd64cd6bfb9234f
+oid sha256:bf840ad1b562e045bc92ac31e01aee8f4cd67d1a73eca73333298edfbae1ad20
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5994e3d2d91a83a07b98e2df8057e08df7ce8afe7d5f64a27b2e29b2d9e5760a
+oid sha256:9b115b07f9fe38375bcc96df9244e270a0061e3396e94a2fc540b35e81b2080b
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bfa72d45322c7889cd0cba044899a675204ad96fd40b4c5e36e86d061721ae8
+oid sha256:709dbfd8db569dd59d549977ea4d372bd8a3fee22ca873f7f07f76ee57da1c03
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e76d1b9e419841ba38c332935be27d6f7d5387bf715355d0d0b0da74e6ad60ee
+oid sha256:d10d973e668b5505b78d845d8bcd5008b3bbe632800fe01e15ed61bbadd63be9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2384,
+  "epoch": 0.24,
   "eval_steps": 500,
-  "global_step": 2980,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1050,6 +1050,13 @@
       "learning_rate": 2.8899655018846297e-05,
       "loss": 3.5125,
       "step": 2980
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 23.667312622070312,
+      "learning_rate": 2.8881318444640564e-05,
+      "loss": 3.5043,
+      "step": 3000
     }
   ],
   "logging_steps": 20,
@@ -1057,7 +1064,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 7043134176854016.0,
+  "total_flos": 7092703910756352.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null