Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27d564dfd34ca6ed990b71480539479284a26817a7d87fe7cd274b9b9f05bf1d
+oid sha256:4dd8a2c113e849af21a4144e319c96a52efc0228fc61e19d51fe106753e669c5
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bad7c271b4c3e7b239656452c0a2e698609e18b95e48a28ccdc9fab19c809048
+oid sha256:534f81a19b2ae93a029c55bfa003a35a49e4bd59a72b433ae75a93a6d7187ec2
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a53dc7b3cb884a4bd850c0601e9089931b7f81afb6e565b337e8e03d83efe328
+oid sha256:8855d313579f39fca8f8bbb5acb04321e0abb8ac2c355b235d16a2f5205f52a5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddaa639affba9b89222fee046caf8a7f8b52a142c3b2d35ccd1f461973cfdc78
+oid sha256:b5b325ea4e14a510f9eb0108f2923753e246a5ec70e919cdd84a9afd64b95afd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008056070248932571,
+  "epoch": 0.0012084105373398855,
   "eval_steps": 4,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -195,6 +195,92 @@
       "eval_samples_per_second": 29.724,
       "eval_steps_per_second": 7.432,
       "step": 20
+    },
+    {
+      "epoch": 0.0008458873761379199,
+      "grad_norm": 2.0658109188079834,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 0.7403,
+      "step": 21
+    },
+    {
+      "epoch": 0.0008861677273825828,
+      "grad_norm": 2.3525924682617188,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 0.7465,
+      "step": 22
+    },
+    {
+      "epoch": 0.0009264480786272456,
+      "grad_norm": 2.358006000518799,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 0.6455,
+      "step": 23
+    },
+    {
+      "epoch": 0.0009667284298719085,
+      "grad_norm": 2.1046624183654785,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 0.5696,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009667284298719085,
+      "eval_loss": 0.6280407905578613,
+      "eval_runtime": 351.4649,
+      "eval_samples_per_second": 29.744,
+      "eval_steps_per_second": 7.437,
+      "step": 24
+    },
+    {
+      "epoch": 0.0010070087811165714,
+      "grad_norm": 1.6811755895614624,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.5188,
+      "step": 25
+    },
+    {
+      "epoch": 0.0010472891323612342,
+      "grad_norm": 2.4113450050354004,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 0.6724,
+      "step": 26
+    },
+    {
+      "epoch": 0.0010875694836058971,
+      "grad_norm": 1.843999981880188,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 0.5452,
+      "step": 27
+    },
+    {
+      "epoch": 0.00112784983485056,
+      "grad_norm": 2.5618975162506104,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 0.7195,
+      "step": 28
+    },
+    {
+      "epoch": 0.00112784983485056,
+      "eval_loss": 0.6231419444084167,
+      "eval_runtime": 351.6375,
+      "eval_samples_per_second": 29.729,
+      "eval_steps_per_second": 7.434,
+      "step": 28
+    },
+    {
+      "epoch": 0.0011681301860952226,
+      "grad_norm": 2.070157766342163,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 0.5124,
+      "step": 29
+    },
+    {
+      "epoch": 0.0012084105373398855,
+      "grad_norm": 1.9961820840835571,
+      "learning_rate": 0.0,
+      "loss": 0.612,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -209,12 +295,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 967722569564160.0,
+  "total_flos": 1451583854346240.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null