Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef3d3ea5ac84b672b30d1cdf4e31f308a42d182e6ea99577d17fdb75980fdfd6
+oid sha256:c8b300e56ec7836f1cdc0219600a45eadcb5320d9f1937c2ec96ce6f6fa0f851
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:737d2d86f3e4c349883e18fb8bc3a0cf3e4ab8c48b719503b889f5f89b64982b
+oid sha256:6df3da8b677f9e341b130e58c010768ac209784cfd6fdad306f3b720d422ea17
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a53b8ad0783113533434bf6d2833e156f7be885b78f1f19b1553288a82e13e2e
+oid sha256:d180772d69b89926e794aa30466cdd606442ea9d66f35dbb2913ac9b66eeae93
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
+oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0014785748812874975,
+  "epoch": 0.002217862321931246,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 83.056,
       "eval_steps_per_second": 41.528,
       "step": 26
+    },
+    {
+      "epoch": 0.0017060479399471126,
+      "grad_norm": 43.454498291015625,
+      "learning_rate": 0.0001,
+      "loss": 11.7852,
+      "step": 30
+    },
+    {
+      "epoch": 0.002217862321931246,
+      "eval_loss": 3.01473331451416,
+      "eval_runtime": 89.5926,
+      "eval_samples_per_second": 82.641,
+      "eval_steps_per_second": 41.32,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 313629622665216.0,
+  "total_flos": 467154612781056.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null