Training in progress, step 32, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59b3ab8b1df8c7dbb70c1aa738717d9974dfc7364347cd05afb11ed8108a092d
+oid sha256:943608aa5c6d1a33cd3de6c65e5e3dc4364cc2718c2e96c2431f1f8af7ed45a8
 size 4969539560

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24fd6512970980552052be46e5e1ffd23abb94389499198cd04131d5c72db1ea
+oid sha256:b0f8c786480fb81dbef237ecccb6d214b6a308947b049039952c10df566011d7
 size 1912795688

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.0,
+  "epoch": 8.0,
   "eval_steps": 100,
-  "global_step": 16,
+  "global_step": 32,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -120,6 +120,118 @@
       "learning_rate": 6.986255778798252e-08,
       "loss": 0.7012,
       "step": 16
+    },
+    {
+      "epoch": 4.290909090909091,
+      "grad_norm": 9.836618423461914,
+      "learning_rate": 6.501344202803413e-08,
+      "loss": 0.777,
+      "step": 17
+    },
+    {
+      "epoch": 4.581818181818182,
+      "grad_norm": 11.242887496948242,
+      "learning_rate": 6.003840142464886e-08,
+      "loss": 0.8631,
+      "step": 18
+    },
+    {
+      "epoch": 4.872727272727273,
+      "grad_norm": 10.001364707946777,
+      "learning_rate": 5.5e-08,
+      "loss": 0.7819,
+      "step": 19
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 10.092758178710938,
+      "learning_rate": 4.996159857535115e-08,
+      "loss": 0.7722,
+      "step": 20
+    },
+    {
+      "epoch": 5.290909090909091,
+      "grad_norm": 9.45466423034668,
+      "learning_rate": 4.498655797196585e-08,
+      "loss": 0.7416,
+      "step": 21
+    },
+    {
+      "epoch": 5.581818181818182,
+      "grad_norm": 10.496912956237793,
+      "learning_rate": 4.0137442212017494e-08,
+      "loss": 0.8161,
+      "step": 22
+    },
+    {
+      "epoch": 5.872727272727273,
+      "grad_norm": 10.202836036682129,
+      "learning_rate": 3.5475231739709885e-08,
+      "loss": 0.823,
+      "step": 23
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 12.920607566833496,
+      "learning_rate": 3.105855655680986e-08,
+      "loss": 0.8315,
+      "step": 24
+    },
+    {
+      "epoch": 6.290909090909091,
+      "grad_norm": 10.253811836242676,
+      "learning_rate": 2.6942958916356994e-08,
+      "loss": 0.8316,
+      "step": 25
+    },
+    {
+      "epoch": 6.581818181818182,
+      "grad_norm": 9.783924102783203,
+      "learning_rate": 2.3180194846605363e-08,
+      "loss": 0.7542,
+      "step": 26
+    },
+    {
+      "epoch": 6.872727272727273,
+      "grad_norm": 10.855210304260254,
+      "learning_rate": 1.981758328893866e-08,
+      "loss": 0.8357,
+      "step": 27
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 10.147912979125977,
+      "learning_rate": 1.6897411034727217e-08,
+      "loss": 0.7426,
+      "step": 28
+    },
+    {
+      "epoch": 7.290909090909091,
+      "grad_norm": 10.078908920288086,
+      "learning_rate": 1.4456400944391145e-08,
+      "loss": 0.7832,
+      "step": 29
+    },
+    {
+      "epoch": 7.581818181818182,
+      "grad_norm": 10.833037376403809,
+      "learning_rate": 1.2525250136123459e-08,
+      "loss": 0.7954,
+      "step": 30
+    },
+    {
+      "epoch": 7.872727272727273,
+      "grad_norm": 9.931336402893066,
+      "learning_rate": 1.1128243951817936e-08,
+      "loss": 0.7893,
+      "step": 31
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 10.87130355834961,
+      "learning_rate": 1.0282950554804083e-08,
+      "loss": 0.9104,
+      "step": 32
     }
   ],
   "logging_steps": 1,
@@ -134,12 +246,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5366131440353280.0,
+  "total_flos": 1.073226288070656e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null