Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6016a91738f92c509fae7473f3f57402eab9ca7b18809aca2dddebeccba1d5a6
+oid sha256:dc479c9ad5f7c3577786474a96a58f84e8fa8d26140b212e02a83b8d7b720cdf
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:708965279644d8d6384f3966c9dcc4ba57135c188ef8f9cff896c2c0f7989c0a
+oid sha256:2785e3908051b37ac33e4ac791b8984a4cf6ff0148d773700dd3f54fe2e57058
 size 197158

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7da5cf41b2b745faed03773025a29a11348f4944822e03e49fca03431b28118
+oid sha256:8d6e215de6b9948b4501fef1f130fef6b44defec3b292330e129f3e70bd52fc7
 size 15024

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": 1.2077073807968648,
+  "epoch": 1.3069888961463096,
   "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": 775.165,
       "eval_steps_per_second": 24.355,
       "step": 462
+    },
+    {
+      "epoch": 1.2155453951665578,
+      "grad_norm": 0.013816201128065586,
+      "learning_rate": 1.2536043909088191e-06,
+      "loss": 11.9293,
+      "step": 465
+    },
+    {
+      "epoch": 1.2233834095362508,
+      "grad_norm": 0.016839459538459778,
+      "learning_rate": 1.0486332583853563e-06,
+      "loss": 11.9467,
+      "step": 468
+    },
+    {
+      "epoch": 1.2312214239059438,
+      "grad_norm": 0.01736452244222164,
+      "learning_rate": 8.617714201998084e-07,
+      "loss": 11.8521,
+      "step": 471
+    },
+    {
+      "epoch": 1.2390594382756368,
+      "grad_norm": 0.025550948455929756,
+      "learning_rate": 6.93088004882253e-07,
+      "loss": 11.6322,
+      "step": 474
+    },
+    {
+      "epoch": 1.2468974526453298,
+      "grad_norm": 0.03142261132597923,
+      "learning_rate": 5.426454159531913e-07,
+      "loss": 12.0707,
+      "step": 477
+    },
+    {
+      "epoch": 1.2547354670150228,
+      "grad_norm": 0.014136346988379955,
+      "learning_rate": 4.104993088376974e-07,
+      "loss": 12.1411,
+      "step": 480
+    },
+    {
+      "epoch": 1.2625734813847158,
+      "grad_norm": 0.023102182894945145,
+      "learning_rate": 2.966985702759828e-07,
+      "loss": 11.8335,
+      "step": 483
+    },
+    {
+      "epoch": 1.2704114957544088,
+      "grad_norm": 0.020949246361851692,
+      "learning_rate": 2.012853002380466e-07,
+      "loss": 11.8762,
+      "step": 486
+    },
+    {
+      "epoch": 1.2782495101241018,
+      "grad_norm": 0.013338472694158554,
+      "learning_rate": 1.2429479634897267e-07,
+      "loss": 11.7727,
+      "step": 489
+    },
+    {
+      "epoch": 1.2860875244937948,
+      "grad_norm": 0.022523999214172363,
+      "learning_rate": 6.575554083078084e-08,
+      "loss": 12.2013,
+      "step": 492
+    },
+    {
+      "epoch": 1.2939255388634878,
+      "grad_norm": 0.016933446750044823,
+      "learning_rate": 2.568918996560532e-08,
+      "loss": 11.8428,
+      "step": 495
+    },
+    {
+      "epoch": 1.3017635532331808,
+      "grad_norm": 0.017216265201568604,
+      "learning_rate": 4.110566084036816e-09,
+      "loss": 11.9056,
+      "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": 8912506060800.0,
+  "total_flos": 9645271941120.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null