Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:845555c6de9615ffd82652772b0c1f13b0219dad9d8411e0092a298a00c8b0e1
+oid sha256:05d5e7678126d1a879f4ffa40be1c01a679c22fe582005a8973619f2557095e5
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb76b5e51d187b4414ca4015838dc1ddf78e15e0bbe33ae525fdded6fbc89403
+oid sha256:4b94a3895c1e6ccfc41429e94316ee871c7dc196191dd303084e2fa53f7b6642
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7370cd9778cec4351056cccc604c313cf532b0f8ca91677580d7717122bd776d
+oid sha256:44627e3dbaee3655496addb0d6d4bce4a40debfebf6c6e10d21a0f2b7bfe9f1f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
+oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02297266253158741,
+  "epoch": 0.03445899379738112,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 14.873,
       "eval_steps_per_second": 7.441,
       "step": 100
+    },
+    {
+      "epoch": 0.02526992878474615,
+      "grad_norm": 2.937729597091675,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 2.206,
+      "step": 110
+    },
+    {
+      "epoch": 0.027567195037904894,
+      "grad_norm": 3.3445348739624023,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 2.2943,
+      "step": 120
+    },
+    {
+      "epoch": 0.029864461291063633,
+      "grad_norm": 2.91733717918396,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 2.1249,
+      "step": 130
+    },
+    {
+      "epoch": 0.03216172754422238,
+      "grad_norm": 3.4622771739959717,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 2.1225,
+      "step": 140
+    },
+    {
+      "epoch": 0.03445899379738112,
+      "grad_norm": 3.4070169925689697,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 2.1542,
+      "step": 150
+    },
+    {
+      "epoch": 0.03445899379738112,
+      "eval_loss": 0.5411030054092407,
+      "eval_runtime": 123.3205,
+      "eval_samples_per_second": 14.864,
+      "eval_steps_per_second": 7.436,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.430851105993523e+16,
+  "total_flos": 5.14408582175785e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null