Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5357fc09f14aca11957c85acc23a6c1f79d5311859edc31bac791dd5ab005a74
+oid sha256:675c8ff64660557f53b38561f37d8c6776269cf97731889db6d83531caef8bc4
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d23dd79972d4a238f6afbf90093086755beb0fdbef11a9dc7d7a310494928c3
+oid sha256:6f762a6c3a764369fe2f84911bc97a130c61234731e5fa88226c5206d99686c4
 size 197158

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1807b6a723a9dd02b18fa5774cf745d7169bae5a5d39fe586fdfa2d5cdd57578
+oid sha256:598ac7ad928dfb5e9c5dc54ca69f59a028ee5757833baba8d3bbe797277eaa95
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41a883c860a264fc5a57d9f8e7a25458dde31e87fca349eec5d367e6dfcc9b75
+oid sha256:450fbd58325e32cc754c9cd91c7ddad3df6c2d035b55d812c9f1629eb0b20102
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6289290891553c37ba97585b94e0d2ee9f0bd3342fa8e89b2d64a0012f2bb90f
+oid sha256:ab493cfda0f259554ebcbaded78ebf98b89c186efad0f2cde1aa0c614556bce7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c32238f7435ba76061ab976f9cfddd71a9091d21054b073cb9871615b3dd3904
+oid sha256:e0d2781671aa3097089e553ce42d712c0bd4e2f148b50bb94c82d661d428cb64
 size 15024

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": 1.0864197530864197,
+  "epoch": 1.1757789535567313,
   "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": 275.908,
       "eval_steps_per_second": 8.67,
       "step": 462
+    },
+    {
+      "epoch": 1.09347442680776,
+      "grad_norm": 0.028014004230499268,
+      "learning_rate": 1.2536043909088191e-06,
+      "loss": 12.2078,
+      "step": 465
+    },
+    {
+      "epoch": 1.1005291005291005,
+      "grad_norm": 0.019710175693035126,
+      "learning_rate": 1.0486332583853563e-06,
+      "loss": 11.932,
+      "step": 468
+    },
+    {
+      "epoch": 1.1075837742504409,
+      "grad_norm": 0.0251897145062685,
+      "learning_rate": 8.617714201998084e-07,
+      "loss": 11.9246,
+      "step": 471
+    },
+    {
+      "epoch": 1.1146384479717812,
+      "grad_norm": 0.020719952881336212,
+      "learning_rate": 6.93088004882253e-07,
+      "loss": 11.9967,
+      "step": 474
+    },
+    {
+      "epoch": 1.1216931216931216,
+      "grad_norm": 0.01866576448082924,
+      "learning_rate": 5.426454159531913e-07,
+      "loss": 11.7563,
+      "step": 477
+    },
+    {
+      "epoch": 1.128747795414462,
+      "grad_norm": 0.029010610654950142,
+      "learning_rate": 4.104993088376974e-07,
+      "loss": 11.9562,
+      "step": 480
+    },
+    {
+      "epoch": 1.1358024691358024,
+      "grad_norm": 0.020120302215218544,
+      "learning_rate": 2.966985702759828e-07,
+      "loss": 12.0342,
+      "step": 483
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.02001938596367836,
+      "learning_rate": 2.012853002380466e-07,
+      "loss": 11.7064,
+      "step": 486
+    },
+    {
+      "epoch": 1.1499118165784832,
+      "grad_norm": 0.021438777446746826,
+      "learning_rate": 1.2429479634897267e-07,
+      "loss": 11.9928,
+      "step": 489
+    },
+    {
+      "epoch": 1.1569664902998236,
+      "grad_norm": 0.016329078003764153,
+      "learning_rate": 6.575554083078084e-08,
+      "loss": 11.9815,
+      "step": 492
+    },
+    {
+      "epoch": 1.164021164021164,
+      "grad_norm": 0.05567369982600212,
+      "learning_rate": 2.568918996560532e-08,
+      "loss": 11.9687,
+      "step": 495
+    },
+    {
+      "epoch": 1.1710758377425043,
+      "grad_norm": 0.026132524013519287,
+      "learning_rate": 4.110566084036816e-09,
+      "loss": 11.8083,
+      "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": 12677572853760.0,
+  "total_flos": 13720076943360.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null