Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23ae89bac01b1983f47ebbd71598a57e302514078d431e7eb6afc8d73076643d
+oid sha256:346a712ed5c1e76bef2fd3cb946bd447597ed9a19b812f1043d01d1e5d557581
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09f2d66f12c15f1c195b4c65479573770a4b3f7f0e92412b2b62ed2e101441c9
+oid sha256:bfec48c8ee43b5b815faba675d9b67c035d55f83b8cec5f8f6b208f954abc2f8
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaef23ad6b9358048cfa2eb81866d8f39693a1c7df686b619cd9d9ea3051d3a5
+oid sha256:b202cc35d4d82828b46ac25c2aa3b0d5b24c9fdd644bb03957f013b307cbc71d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
+oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007329321811518798,
+  "epoch": 0.008143690901687553,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 12.934,
       "eval_steps_per_second": 1.617,
       "step": 81
+    },
+    {
+      "epoch": 0.007600778174908384,
+      "grad_norm": 2.635622501373291,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 0.5012,
+      "step": 84
+    },
+    {
+      "epoch": 0.00787223453829797,
+      "grad_norm": 1.4843945503234863,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 0.4902,
+      "step": 87
+    },
+    {
+      "epoch": 0.008143690901687553,
+      "grad_norm": 1.9264837503433228,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.4289,
+      "step": 90
+    },
+    {
+      "epoch": 0.008143690901687553,
+      "eval_loss": 0.48586252331733704,
+      "eval_runtime": 1438.3431,
+      "eval_samples_per_second": 12.941,
+      "eval_steps_per_second": 1.618,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1697923788111872e+17,
+  "total_flos": 1.299769309790208e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null