Training in progress, step 12, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:267b16c5ccdee00137664da4abae275386662939fb4daaa5e60ac9518090836d
+oid sha256:c357c5798fa383f703e3104a2163893d8dcc46cb307fed3d6be7fad4e4d969a0
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c18f7424f1e4e6d1cb96908353fde53bda9527acd5db49971fbc85fb35606968
+oid sha256:05a24b933e64750875063a9fdb13416eb25bfe2ba021d748276bb4d9dfc175e1
 size 263024

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c17f63e4ecde32684d8daab508bc95e4fb60b42da6dcad237c0dd3151be21cc8
+oid sha256:0763de3baeafeae3c2d3e86c5cca4b3cc84990c5ec7370d1efbdc258d9c92b9e
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:799b858ba8010cc95a2389340a76b52c936dc0a7ec275440a87d94d2e452dd32
+oid sha256:065afe6921dc44b326c807bd7c974bd67953ebe0d6cb5a88844e20eec41e990c
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f18136116fbbf8d9b045c7ff28443c53f7143d67a0ce6c8ba325061eccf527c
+oid sha256:596789201c88c01c6a7d22abf9f027c8205c302d5ac99f17af7a17d4798e20f6
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:198d94423ce31e2d2b592f219e2eca5d02a987fb1a82bd5a9e9797758ceb1f92
+oid sha256:4796e9c4b19daacde1fee3098e9336d004c73055fbb914384ea17132827c918b
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e24a6b926ea4352d6ea08b02a2fd5fd4abd5648492cff00d926548288e954fe2
+oid sha256:4c85242bd6c01b1010db2878bf11b1daea2210fa9ee2e97e50a834d7598913ba
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:093b1428faca2f70382056a803de21d329871ce63be030b0986cb42c8e5131d5
+oid sha256:d24fb8c54add3548a3355e7dc06b22feea802f72fb85be789a378e2b05b2928d
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a65661ebaf88a59c39ed172576b3b283adce8bd38b021ba8cb4f51a54d74663c
+oid sha256:6beda985a90f4f29b81a083490a1b9556b5ecff089aa11d87d2a514ed5ece73b
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3998529b7cdd0eabe7e1c8d3a03005ab0e866780f30f07533f233bc623c1f71c
+oid sha256:3fab81e9f62516ca077b4e54e2b4e12cf8cb691a7b37fb91d5007f7d4a325c61
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
+oid sha256:927392b6637f3067ac6cd161b66dd1bd3f9eddd413bfb8664dee51030ef53388
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5565217391304348,
+  "epoch": 0.8347826086956521,
   "eval_steps": 4,
-  "global_step": 8,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -87,6 +87,42 @@
       "eval_samples_per_second": 909.671,
       "eval_steps_per_second": 121.915,
       "step": 8
+    },
+    {
+      "epoch": 0.6260869565217392,
+      "grad_norm": 7.649663925170898,
+      "learning_rate": 9e-05,
+      "loss": 177.1172,
+      "step": 9
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 7.564890384674072,
+      "learning_rate": 0.0001,
+      "loss": 177.0859,
+      "step": 10
+    },
+    {
+      "epoch": 0.7652173913043478,
+      "grad_norm": 8.557611465454102,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 177.0078,
+      "step": 11
+    },
+    {
+      "epoch": 0.8347826086956521,
+      "grad_norm": 7.719607353210449,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 176.9453,
+      "step": 12
+    },
+    {
+      "epoch": 0.8347826086956521,
+      "eval_loss": 11.049612998962402,
+      "eval_runtime": 0.1071,
+      "eval_samples_per_second": 905.76,
+      "eval_steps_per_second": 121.391,
+      "step": 12
     }
   ],
   "logging_steps": 1,
@@ -106,7 +142,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 10649371410432.0,
+  "total_flos": 15974057115648.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null