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:f50801ca7fdea39ab8dffd8246fb170afc53418cabe1fa04245417373645482a
+oid sha256:acc6c4e785016d48b012ad12d44c86d4b4acd25af4459f9de8cb08dbd59273f3
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6ee54638816f60627fe6da0187befe39f9d5e4113122bcd4fd88bb1acb59217
+oid sha256:4be198a3385cb9cd754dd2e760701e64fe2813f33e1d613d40bf625d12a88120
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e95801a4c403b551085cb43e2962db50d33a2ed7cc9363c38784e3077ff4975
+oid sha256:d69b2a85ea7d417ca994661c4c15854ba7a22dba6304c7fa9427373d17d5225c
 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": 0.022113544546034446,
+  "epoch": 0.03317031681905167,
   "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": 27.341,
       "eval_steps_per_second": 13.698,
       "step": 26
+    },
+    {
+      "epoch": 0.022964065490112696,
+      "grad_norm": 3.840120553970337,
+      "learning_rate": 3.083613409639764e-05,
+      "loss": 6.86,
+      "step": 27
+    },
+    {
+      "epoch": 0.023814586434190942,
+      "grad_norm": 5.417391777038574,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 7.7778,
+      "step": 28
+    },
+    {
+      "epoch": 0.02466510737826919,
+      "grad_norm": 3.8475501537323,
+      "learning_rate": 2.6961477393196126e-05,
+      "loss": 5.9285,
+      "step": 29
+    },
+    {
+      "epoch": 0.02551562832234744,
+      "grad_norm": 4.8878374099731445,
+      "learning_rate": 2.5e-05,
+      "loss": 7.3934,
+      "step": 30
+    },
+    {
+      "epoch": 0.026366149266425686,
+      "grad_norm": 4.846117973327637,
+      "learning_rate": 2.303852260680388e-05,
+      "loss": 7.3275,
+      "step": 31
+    },
+    {
+      "epoch": 0.027216670210503932,
+      "grad_norm": 3.879229784011841,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 6.676,
+      "step": 32
+    },
+    {
+      "epoch": 0.028067191154582182,
+      "grad_norm": 5.315415859222412,
+      "learning_rate": 1.9163865903602374e-05,
+      "loss": 7.6324,
+      "step": 33
+    },
+    {
+      "epoch": 0.02891771209866043,
+      "grad_norm": 4.311729907989502,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 6.9114,
+      "step": 34
+    },
+    {
+      "epoch": 0.02976823304273868,
+      "grad_norm": 6.797874450683594,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 8.9163,
+      "step": 35
+    },
+    {
+      "epoch": 0.030618753986816925,
+      "grad_norm": 6.546699047088623,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 9.0227,
+      "step": 36
+    },
+    {
+      "epoch": 0.03146927493089517,
+      "grad_norm": 4.277498722076416,
+      "learning_rate": 1.1937535882101281e-05,
+      "loss": 7.4829,
+      "step": 37
+    },
+    {
+      "epoch": 0.03231979587497342,
+      "grad_norm": 5.2016143798828125,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 7.472,
+      "step": 38
+    },
+    {
+      "epoch": 0.03317031681905167,
+      "grad_norm": 4.864084243774414,
+      "learning_rate": 8.763798791745411e-06,
+      "loss": 8.2183,
+      "step": 39
+    },
+    {
+      "epoch": 0.03317031681905167,
+      "eval_loss": 1.9271198511123657,
+      "eval_runtime": 18.0882,
+      "eval_samples_per_second": 27.366,
+      "eval_steps_per_second": 13.711,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4316142810169344.0,
+  "total_flos": 6514932543651840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null