Training in progress, step 136, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c51bb1bd493fedab904030a7482e3c21bba78bd2533b6b08b9c73123b0a35d3a
+oid sha256:a720b6a6c737c244779f324a7a933055b8a6b1988a5156e8fd556928b0ac95dd
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b99ee001fbe78e978d9a8949cfacde0ed77f2b37b4f24cd265a5eb26ee84e83d
+oid sha256:cef617551b0809384d4da27a93c36dcd3801b5789a571da1dce0485f8e7f3302
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5232f719bd209899927dac4f0c85d3dc677af3c55e9d27e5ace57effddf642d1
+oid sha256:6e554c518f56e093745f46f37d2f62ebbef88c44083698dc01d4c782697c6d2b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c91934808157be4b4581cbac88c1dcb8ab73e7092f7b8aa05c4fbac8ab77615f
+oid sha256:ffd0ef2a827b219b75915f5a88a30c53ebe86f536eec93a6252baab983329eb7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.030542188001283284,
+  "epoch": 0.03490535771575232,
   "eval_steps": 17,
-  "global_step": 119,
+  "global_step": 136,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -344,6 +344,56 @@
       "eval_samples_per_second": 13.282,
       "eval_steps_per_second": 1.662,
       "step": 119
+    },
+    {
+      "epoch": 0.030798845043310877,
+      "grad_norm": 0.41164785623550415,
+      "learning_rate": 3.772572564296005e-05,
+      "loss": 2.2888,
+      "step": 120
+    },
+    {
+      "epoch": 0.031568816169393644,
+      "grad_norm": 0.3949745297431946,
+      "learning_rate": 3.533749813077677e-05,
+      "loss": 2.2659,
+      "step": 123
+    },
+    {
+      "epoch": 0.03233878729547642,
+      "grad_norm": 0.31058645248413086,
+      "learning_rate": 3.298534127791785e-05,
+      "loss": 2.3101,
+      "step": 126
+    },
+    {
+      "epoch": 0.03310875842155919,
+      "grad_norm": 0.3842872977256775,
+      "learning_rate": 3.0675041535377405e-05,
+      "loss": 2.1922,
+      "step": 129
+    },
+    {
+      "epoch": 0.03387872954764196,
+      "grad_norm": 0.37319129705429077,
+      "learning_rate": 2.8412282383075363e-05,
+      "loss": 2.251,
+      "step": 132
+    },
+    {
+      "epoch": 0.03464870067372473,
+      "grad_norm": 0.3240547180175781,
+      "learning_rate": 2.6202630348146324e-05,
+      "loss": 2.3064,
+      "step": 135
+    },
+    {
+      "epoch": 0.03490535771575232,
+      "eval_loss": 2.2887308597564697,
+      "eval_runtime": 494.1479,
+      "eval_samples_per_second": 13.281,
+      "eval_steps_per_second": 1.661,
+      "step": 136
     }
   ],
   "logging_steps": 3,
@@ -363,7 +413,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7469611905646592e+17,
+  "total_flos": 2.004061139364741e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null