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:f615420f5a3bc4ef2b1a3b44256a7ee7e875158dae015a1856a7ae4183295e4b
+oid sha256:5d1538236166ec71cef807e2fc45c4c4762f1856bf61328120d2819153d88b9a
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dfdf70d3ae2c692e22aec88d3b10321f6ff4b0dc710187cb565b9898e11b662
+oid sha256:4c35993ffd92f1a44d7f446620c4611fbe35c89560a672a78431f4231f32eaf3
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424d06375131df3df5d4883391c61f995c66d877e893fd245f2c624058954297
+oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09737827715355805,
+  "epoch": 0.14606741573033707,
   "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": 31.834,
       "eval_steps_per_second": 15.917,
       "step": 26
+    },
+    {
+      "epoch": 0.10112359550561797,
+      "grad_norm": 1.6498875617980957,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 1.6355,
+      "step": 27
+    },
+    {
+      "epoch": 0.10486891385767791,
+      "grad_norm": 1.5848513841629028,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 1.4611,
+      "step": 28
+    },
+    {
+      "epoch": 0.10861423220973783,
+      "grad_norm": 1.6103304624557495,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 1.463,
+      "step": 29
+    },
+    {
+      "epoch": 0.11235955056179775,
+      "grad_norm": 1.4713010787963867,
+      "learning_rate": 5e-05,
+      "loss": 1.4531,
+      "step": 30
+    },
+    {
+      "epoch": 0.11610486891385768,
+      "grad_norm": 1.4418309926986694,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 1.4607,
+      "step": 31
+    },
+    {
+      "epoch": 0.1198501872659176,
+      "grad_norm": 1.3354123830795288,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.4086,
+      "step": 32
+    },
+    {
+      "epoch": 0.12359550561797752,
+      "grad_norm": 1.5024315118789673,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 1.4571,
+      "step": 33
+    },
+    {
+      "epoch": 0.12734082397003746,
+      "grad_norm": 1.4268651008605957,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.3551,
+      "step": 34
+    },
+    {
+      "epoch": 0.13108614232209737,
+      "grad_norm": 1.4591658115386963,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.3186,
+      "step": 35
+    },
+    {
+      "epoch": 0.1348314606741573,
+      "grad_norm": 1.5342679023742676,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 1.1651,
+      "step": 36
+    },
+    {
+      "epoch": 0.13857677902621723,
+      "grad_norm": 1.763529896736145,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 1.1908,
+      "step": 37
+    },
+    {
+      "epoch": 0.14232209737827714,
+      "grad_norm": 1.6287809610366821,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.4347,
+      "step": 38
+    },
+    {
+      "epoch": 0.14606741573033707,
+      "grad_norm": 1.562390923500061,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 1.4056,
+      "step": 39
+    },
+    {
+      "epoch": 0.14606741573033707,
+      "eval_loss": 1.3499964475631714,
+      "eval_runtime": 14.1251,
+      "eval_samples_per_second": 31.858,
+      "eval_steps_per_second": 15.929,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.252501995015373e+16,
+  "total_flos": 3.360794548371456e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null