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:a6b865612dde64b5d653272d7d77c6def5f865ac2b145abc14a3dc6ad5390f01
+oid sha256:10a0fbf9f423d72eaec32373989b7ae375070b0dfc853da3bb6ecac203352027
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c763d247aa63f54eec7d082acfd4e963f4a108f27e6075911554ff8301c43b4
+oid sha256:aff7e810c30c877c5ef5dd36fe9d7a5b2607adaa9004758d54b9ee27f2558a30
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63076df0e2f5c2eff0ee92071ec83ec94c981f8fbd2f640764417db149cee50d
+oid sha256:8a09ad7e826d10efce700906e00267beeb0fde82aeff880f7721e7c0c6d184a9
 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": 0.0008128098837681866,
+  "epoch": 0.00121921482565228,
   "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": 41.072,
       "eval_steps_per_second": 10.271,
       "step": 20
+    },
+    {
+      "epoch": 0.000853450377956596,
+      "grad_norm": 0.03175048530101776,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 11.7641,
+      "step": 21
+    },
+    {
+      "epoch": 0.0008940908721450052,
+      "grad_norm": 0.025317387655377388,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 11.7663,
+      "step": 22
+    },
+    {
+      "epoch": 0.0009347313663334146,
+      "grad_norm": 0.02416888065636158,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 11.7631,
+      "step": 23
+    },
+    {
+      "epoch": 0.000975371860521824,
+      "grad_norm": 0.033092666417360306,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 11.7622,
+      "step": 24
+    },
+    {
+      "epoch": 0.000975371860521824,
+      "eval_loss": 11.76446533203125,
+      "eval_runtime": 252.0607,
+      "eval_samples_per_second": 41.105,
+      "eval_steps_per_second": 10.279,
+      "step": 24
+    },
+    {
+      "epoch": 0.0010160123547102334,
+      "grad_norm": 0.0314379446208477,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 11.7653,
+      "step": 25
+    },
+    {
+      "epoch": 0.0010566528488986425,
+      "grad_norm": 0.019938500598073006,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 11.7634,
+      "step": 26
+    },
+    {
+      "epoch": 0.0010972933430870519,
+      "grad_norm": 0.029247622936964035,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 11.7648,
+      "step": 27
+    },
+    {
+      "epoch": 0.0011379338372754612,
+      "grad_norm": 0.02898564375936985,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 11.7689,
+      "step": 28
+    },
+    {
+      "epoch": 0.0011379338372754612,
+      "eval_loss": 11.764463424682617,
+      "eval_runtime": 252.4728,
+      "eval_samples_per_second": 41.038,
+      "eval_steps_per_second": 10.262,
+      "step": 28
+    },
+    {
+      "epoch": 0.0011785743314638706,
+      "grad_norm": 0.02746054343879223,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 11.7606,
+      "step": 29
+    },
+    {
+      "epoch": 0.00121921482565228,
+      "grad_norm": 0.029992183670401573,
+      "learning_rate": 0.0,
+      "loss": 11.7663,
+      "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": 2037000437760.0,
+  "total_flos": 3055500656640.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null