Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc09b6d832460f6125f2db8055c6f9f537d1ea3414f1f8a8a8e22b7efa3fa616
+oid sha256:1f4a7691e7cd2fe5785a78bf212d26aadf3c814be08b43ca6e24094b93d1b632
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:157cd5c27e1bbfa5f91dac42e11035af12e5b2d92b54551902af11acc1b94a7c
+oid sha256:69815d0b02d4093787212496ad1c2421e8902a92e6bb004f8d5dfeda4e261b07
 size 81730196

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e79f6ba8fb7ffd48989487f6e68f93db591e92af3a69e568722794c031540f83
+oid sha256:dc0d6a68d922e782698a018376b53b85027f73e542c47378e687b580096f86bd
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecf7ec282beb1f61e959b9e912d5b9b4c3128e903769f4f35493243fd1bdc61b
+oid sha256:57c230e4a3d3176d8f4a84949e99fccf4bc6db16aab7ec60a204be03a7a4d58c
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
+oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3657142857142857,
+  "epoch": 0.5485714285714286,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 11.595,
       "eval_steps_per_second": 2.905,
       "step": 26
+    },
+    {
+      "epoch": 0.3797802197802198,
+      "grad_norm": 0.1247800961136818,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.7944,
+      "step": 27
+    },
+    {
+      "epoch": 0.39384615384615385,
+      "grad_norm": 0.11753375828266144,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7916,
+      "step": 28
+    },
+    {
+      "epoch": 0.40791208791208794,
+      "grad_norm": 0.10586351901292801,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7824,
+      "step": 29
+    },
+    {
+      "epoch": 0.421978021978022,
+      "grad_norm": 0.10135481506586075,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7672,
+      "step": 30
+    },
+    {
+      "epoch": 0.43604395604395607,
+      "grad_norm": 0.10301663726568222,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.7961,
+      "step": 31
+    },
+    {
+      "epoch": 0.4501098901098901,
+      "grad_norm": 0.1041460931301117,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7891,
+      "step": 32
+    },
+    {
+      "epoch": 0.4641758241758242,
+      "grad_norm": 0.09919846802949905,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8119,
+      "step": 33
+    },
+    {
+      "epoch": 0.47824175824175824,
+      "grad_norm": 0.09898246824741364,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7787,
+      "step": 34
+    },
+    {
+      "epoch": 0.49230769230769234,
+      "grad_norm": 0.10475801676511765,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.7885,
+      "step": 35
+    },
+    {
+      "epoch": 0.5063736263736264,
+      "grad_norm": 0.09680575132369995,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7795,
+      "step": 36
+    },
+    {
+      "epoch": 0.5204395604395604,
+      "grad_norm": 0.10325780510902405,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7897,
+      "step": 37
+    },
+    {
+      "epoch": 0.5345054945054946,
+      "grad_norm": 0.09474309533834457,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7936,
+      "step": 38
+    },
+    {
+      "epoch": 0.5485714285714286,
+      "grad_norm": 0.09674929827451706,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.8068,
+      "step": 39
+    },
+    {
+      "epoch": 0.5485714285714286,
+      "eval_loss": 0.7735550403594971,
+      "eval_runtime": 41.3006,
+      "eval_samples_per_second": 11.598,
+      "eval_steps_per_second": 2.906,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.484798907735081e+17,
+  "total_flos": 8.227198361602621e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null