Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3d71f135aaf51849845b589a0599d3e3c87aa7bb1cbd6352df3fb636193a03b
+oid sha256:a82d599d09af54b3c7a2840cebd545bc2273f0a5b8ed60bb5b04531b201ad48b
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfe1fa92a7323db508573f5ba92831f8d0c60c3665cbbe91b3e18368afe5ddfe
+oid sha256:a662c90f15910aa7edf829fa148b39f2be1de574dad823a28100b8459b300468
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35955a38f305f08a71cf5a6aeede99e60dbfc9c66fbb6b89f8f788d949eaddfc
+oid sha256:83b754e0af1895f139eed8d3cc5238b83eb4f00cecad4c166ba0d08eaf88e419
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b58b44a2d5024ddc12e64ead45d5d25c7fc985d9aaeb44c7bc3de9b8cf56f23
+oid sha256:fe1d153de177b356f9e3a70d6e4ec979560b0c300994e71ca4cb89afc74c5b3a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.504885993485342,
+  "epoch": 1.6286644951140063,
   "eval_steps": 42,
-  "global_step": 462,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1181,6 +1181,90 @@
       "eval_samples_per_second": 23.241,
       "eval_steps_per_second": 5.844,
       "step": 462
+    },
+    {
+      "epoch": 1.514657980456026,
+      "grad_norm": 2.5057575702667236,
+      "learning_rate": 1.2536043909088191e-06,
+      "loss": 0.8524,
+      "step": 465
+    },
+    {
+      "epoch": 1.52442996742671,
+      "grad_norm": 2.9005579948425293,
+      "learning_rate": 1.0486332583853563e-06,
+      "loss": 0.8315,
+      "step": 468
+    },
+    {
+      "epoch": 1.5342019543973942,
+      "grad_norm": 2.7489733695983887,
+      "learning_rate": 8.617714201998084e-07,
+      "loss": 0.7929,
+      "step": 471
+    },
+    {
+      "epoch": 1.5439739413680782,
+      "grad_norm": 2.5570104122161865,
+      "learning_rate": 6.93088004882253e-07,
+      "loss": 0.9023,
+      "step": 474
+    },
+    {
+      "epoch": 1.5537459283387622,
+      "grad_norm": 2.6289138793945312,
+      "learning_rate": 5.426454159531913e-07,
+      "loss": 0.861,
+      "step": 477
+    },
+    {
+      "epoch": 1.5635179153094463,
+      "grad_norm": 2.8074800968170166,
+      "learning_rate": 4.104993088376974e-07,
+      "loss": 0.6996,
+      "step": 480
+    },
+    {
+      "epoch": 1.5732899022801303,
+      "grad_norm": 2.5680346488952637,
+      "learning_rate": 2.966985702759828e-07,
+      "loss": 0.9349,
+      "step": 483
+    },
+    {
+      "epoch": 1.5830618892508144,
+      "grad_norm": 2.4893345832824707,
+      "learning_rate": 2.012853002380466e-07,
+      "loss": 0.7033,
+      "step": 486
+    },
+    {
+      "epoch": 1.5928338762214984,
+      "grad_norm": 2.6643295288085938,
+      "learning_rate": 1.2429479634897267e-07,
+      "loss": 0.7915,
+      "step": 489
+    },
+    {
+      "epoch": 1.6026058631921825,
+      "grad_norm": 2.4373981952667236,
+      "learning_rate": 6.575554083078084e-08,
+      "loss": 0.803,
+      "step": 492
+    },
+    {
+      "epoch": 1.6123778501628665,
+      "grad_norm": 2.700291872024536,
+      "learning_rate": 2.568918996560532e-08,
+      "loss": 0.8002,
+      "step": 495
+    },
+    {
+      "epoch": 1.6221498371335505,
+      "grad_norm": 2.6518638134002686,
+      "learning_rate": 4.110566084036816e-09,
+      "loss": 0.7295,
+      "step": 498
     }
   ],
   "logging_steps": 3,
@@ -1195,12 +1279,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.484194956409569e+17,
+  "total_flos": 3.770812536371282e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null