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:f9eab3ee6e4809088a4c6ceff92ac8d7d8a7e5df1a875e21574574434b01af97
+oid sha256:4298a07d99fa7b5cbb094d3eccaa8136a4cdab0e01a11cb92c0bf9b005905478
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf1f25fb0a2aead05f9a88ad3ffcbfe707abc453dcc2f7bccd399cdbd5e69391
+oid sha256:3d01cefa21371013284128a37863c0ea4157c37f1b0dabff9db481dbd74f82bd
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ab9c123c3888632970748b04b0ed0f8e6bfe7e4410afce747b003ab093b8d1b
+oid sha256:5a4db09ef2741774904f678e0a1fe282640cbcfd08000ed9834754dfc73628ea
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09576427255985268,
+  "epoch": 0.1841620626151013,
   "eval_steps": 10,
-  "global_step": 26,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -66,6 +66,65 @@
       "learning_rate": 6.91341716182545e-05,
       "loss": 44.2816,
       "step": 25
+    },
+    {
+      "epoch": 0.11049723756906077,
+      "grad_norm": 2.4358975887298584,
+      "learning_rate": 5e-05,
+      "loss": 44.2062,
+      "step": 30
+    },
+    {
+      "epoch": 0.11049723756906077,
+      "eval_loss": 11.042398452758789,
+      "eval_runtime": 0.5742,
+      "eval_samples_per_second": 200.267,
+      "eval_steps_per_second": 101.004,
+      "step": 30
+    },
+    {
+      "epoch": 0.1289134438305709,
+      "grad_norm": 2.4555740356445312,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 44.1368,
+      "step": 35
+    },
+    {
+      "epoch": 0.14732965009208104,
+      "grad_norm": 2.4573967456817627,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 44.0853,
+      "step": 40
+    },
+    {
+      "epoch": 0.14732965009208104,
+      "eval_loss": 11.021912574768066,
+      "eval_runtime": 0.615,
+      "eval_samples_per_second": 186.977,
+      "eval_steps_per_second": 94.301,
+      "step": 40
+    },
+    {
+      "epoch": 0.16574585635359115,
+      "grad_norm": 2.5920231342315674,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 44.09,
+      "step": 45
+    },
+    {
+      "epoch": 0.1841620626151013,
+      "grad_norm": 2.5824270248413086,
+      "learning_rate": 0.0,
+      "loss": 44.0651,
+      "step": 50
+    },
+    {
+      "epoch": 0.1841620626151013,
+      "eval_loss": 11.01814079284668,
+      "eval_runtime": 0.578,
+      "eval_samples_per_second": 198.979,
+      "eval_steps_per_second": 100.354,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -80,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 262820855808.0,
+  "total_flos": 508763308032.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null