Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70ed621bafff4f5f266db7ff95c269580b76b660cecd9b8d6e5c92f14bc69c43
+oid sha256:7cecb0dd61835862141a9fd4c09dbf1165776116f396aac26a4009636473aae1
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f4bc4713ff79647dd200ddea32de1ed10406a913799534076205061c8ff771e
+oid sha256:885a929d7fd40c1a65db0355470111abcafcb50984a22e57b1af74bf51e47a94
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4403875ec607cf3108caac6354185aadd4588ae4b29cc7dad762431733537e30
+oid sha256:89ffcad5a84b06fde95717df10413749838a6b711ecc83f3ebee00a93d200145
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008865550516588809,
+  "epoch": 0.0011366090405883088,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 11.9331,
       "step": 35
+    },
+    {
+      "epoch": 0.0009092872324706471,
+      "grad_norm": 0.10718891769647598,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9431,
+      "step": 40
+    },
+    {
+      "epoch": 0.0009092872324706471,
+      "eval_loss": 11.938214302062988,
+      "eval_runtime": 534.3849,
+      "eval_samples_per_second": 34.662,
+      "eval_steps_per_second": 17.332,
+      "step": 40
+    },
+    {
+      "epoch": 0.001022948136529478,
+      "grad_norm": 0.09115225076675415,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9356,
+      "step": 45
+    },
+    {
+      "epoch": 0.0011366090405883088,
+      "grad_norm": 0.11200302839279175,
+      "learning_rate": 0.0,
+      "loss": 11.937,
+      "step": 50
+    },
+    {
+      "epoch": 0.0011366090405883088,
+      "eval_loss": 11.938163757324219,
+      "eval_runtime": 534.83,
+      "eval_samples_per_second": 34.633,
+      "eval_steps_per_second": 17.318,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8260291657728.0,
+  "total_flos": 10575676440576.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null