Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:728640654e988d33ae1b19807c17962fbecb7f4539508fa7d4e550799f5a4ec1
+oid sha256:d8e2ebb1c128ba520907091bd9a326f5b6b0119954308f908082337d256e1711
 size 10636096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621ad30317a05a04ffab2964470fc5da31adfb53e8ae89885bf7fa1dda6aef22
+oid sha256:2ef90f96e9bc8935d244b5a0daea752baeadad432be6e56319f45074834b734b
 size 21354682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc9ae2e2480f59398089eab9cb7f09c32d8c69a0c89598a00f9a624fdbb0855b
+oid sha256:a56f2618a2cc50a494d72bb90d568c6c748a64872c9527423c54ff20d17de02d
 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": 0.08048289738430583,
+  "epoch": 0.12072434607645875,
   "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": 65.012,
       "eval_steps_per_second": 16.717,
       "step": 20
+    },
+    {
+      "epoch": 0.08450704225352113,
+      "grad_norm": 2.448875665664673,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 7.8969,
+      "step": 21
+    },
+    {
+      "epoch": 0.08853118712273642,
+      "grad_norm": 2.487572193145752,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 6.285,
+      "step": 22
+    },
+    {
+      "epoch": 0.0925553319919517,
+      "grad_norm": 2.300093412399292,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 6.6932,
+      "step": 23
+    },
+    {
+      "epoch": 0.096579476861167,
+      "grad_norm": 2.773916006088257,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 7.0114,
+      "step": 24
+    },
+    {
+      "epoch": 0.096579476861167,
+      "eval_loss": 3.917163133621216,
+      "eval_runtime": 1.6764,
+      "eval_samples_per_second": 62.632,
+      "eval_steps_per_second": 16.105,
+      "step": 24
+    },
+    {
+      "epoch": 0.1006036217303823,
+      "grad_norm": 2.337402582168579,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 7.3169,
+      "step": 25
+    },
+    {
+      "epoch": 0.10462776659959759,
+      "grad_norm": 2.8300514221191406,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 7.2812,
+      "step": 26
+    },
+    {
+      "epoch": 0.10865191146881288,
+      "grad_norm": 3.735287666320801,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 7.1474,
+      "step": 27
+    },
+    {
+      "epoch": 0.11267605633802817,
+      "grad_norm": 2.840820074081421,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 7.8008,
+      "step": 28
+    },
+    {
+      "epoch": 0.11267605633802817,
+      "eval_loss": 3.920280933380127,
+      "eval_runtime": 1.6256,
+      "eval_samples_per_second": 64.591,
+      "eval_steps_per_second": 16.609,
+      "step": 28
+    },
+    {
+      "epoch": 0.11670020120724346,
+      "grad_norm": 2.6696712970733643,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 7.3584,
+      "step": 29
+    },
+    {
+      "epoch": 0.12072434607645875,
+      "grad_norm": 2.626060962677002,
+      "learning_rate": 0.0,
+      "loss": 7.9641,
+      "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": 86195463782400.0,
+  "total_flos": 129293195673600.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null