Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:628fa114efbdc209508007e11d42fde209c5eb874335c46f0a33087ef72028cf
+oid sha256:e17ee3032720a311864414326cdc1dedff83892119d6c3a0339c2dfa62e9c1ba
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a9e96e11af229cd7f04dc268a161f5c152aaf2fad77fb70bf42852c34b1affc
+oid sha256:32fd2332ece9d4716670c04f57b40198cab2838374944f55cd275a60da75ca0d
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e20e6cf25df1a73c081a325508521e0a139527415aa1406a7206400010e5059a
+oid sha256:0591677270b8f946406201eacfc330e8e8ee74aa2b0abf0016ba0d47af13c558
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
+oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011057947900053162,
+  "epoch": 0.016586921850079744,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 11.023,
       "eval_steps_per_second": 5.511,
       "step": 26
+    },
+    {
+      "epoch": 0.011483253588516746,
+      "grad_norm": 0.3313671350479126,
+      "learning_rate": 3.083613409639764e-05,
+      "loss": 0.7642,
+      "step": 27
+    },
+    {
+      "epoch": 0.01190855927698033,
+      "grad_norm": 0.37808409333229065,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 0.7655,
+      "step": 28
+    },
+    {
+      "epoch": 0.012333864965443912,
+      "grad_norm": 0.3844619691371918,
+      "learning_rate": 2.6961477393196126e-05,
+      "loss": 0.8025,
+      "step": 29
+    },
+    {
+      "epoch": 0.012759170653907496,
+      "grad_norm": 0.37186184525489807,
+      "learning_rate": 2.5e-05,
+      "loss": 0.8364,
+      "step": 30
+    },
+    {
+      "epoch": 0.01318447634237108,
+      "grad_norm": 0.310320645570755,
+      "learning_rate": 2.303852260680388e-05,
+      "loss": 0.6388,
+      "step": 31
+    },
+    {
+      "epoch": 0.013609782030834662,
+      "grad_norm": 0.3105718493461609,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 0.7279,
+      "step": 32
+    },
+    {
+      "epoch": 0.014035087719298246,
+      "grad_norm": 0.3364258110523224,
+      "learning_rate": 1.9163865903602374e-05,
+      "loss": 0.7568,
+      "step": 33
+    },
+    {
+      "epoch": 0.014460393407761828,
+      "grad_norm": 0.34743359684944153,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.7706,
+      "step": 34
+    },
+    {
+      "epoch": 0.014885699096225412,
+      "grad_norm": 0.29443031549453735,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.7154,
+      "step": 35
+    },
+    {
+      "epoch": 0.015311004784688996,
+      "grad_norm": 0.3357723653316498,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 0.752,
+      "step": 36
+    },
+    {
+      "epoch": 0.01573631047315258,
+      "grad_norm": 0.2919500470161438,
+      "learning_rate": 1.1937535882101281e-05,
+      "loss": 0.7965,
+      "step": 37
+    },
+    {
+      "epoch": 0.01616161616161616,
+      "grad_norm": 0.27403074502944946,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 0.7265,
+      "step": 38
+    },
+    {
+      "epoch": 0.016586921850079744,
+      "grad_norm": 0.27928847074508667,
+      "learning_rate": 8.763798791745411e-06,
+      "loss": 0.6562,
+      "step": 39
+    },
+    {
+      "epoch": 0.016586921850079744,
+      "eval_loss": 0.7195438146591187,
+      "eval_runtime": 90.1408,
+      "eval_samples_per_second": 10.983,
+      "eval_steps_per_second": 5.491,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.591018229071872e+16,
+  "total_flos": 2.366738559664128e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null