Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:050e993398a3484e237b3a0e4862a12d4265fbd7cbc7c09d136af21c83c55624
+oid sha256:cead8642df60f1a5ffbdbffbb252762321d5d0479ed722b82e9ae8186a31be7e
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94b5e671e20bc397b60e10727f7c7d9ef7f42ab97b03f390c8f0eea48e2360f4
+oid sha256:2a9def7dd7f9552aa09238e22aa685d5b21066cfdbafe738b1aea76f22053c55
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a94f71583a2db5b8ba4d02c25110e0306a52ff18ad6f58f0328171065b53430c
+oid sha256:238d91f489adef697523368efde471946ec4962b97178a433b03cee9c743141e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e92785679980f3fcd23b14ce1acaffcae115e3e9164492d0e4b31775d32447
+oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003145795523290986,
+  "epoch": 0.006291591046581972,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 50.255,
       "eval_steps_per_second": 25.127,
       "step": 13
+    },
+    {
+      "epoch": 0.0033877797943133695,
+      "grad_norm": 4.443027973175049,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 6.2077,
+      "step": 14
+    },
+    {
+      "epoch": 0.003629764065335753,
+      "grad_norm": 3.561443567276001,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 6.7655,
+      "step": 15
+    },
+    {
+      "epoch": 0.0038717483363581366,
+      "grad_norm": 4.5063886642456055,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 6.4769,
+      "step": 16
+    },
+    {
+      "epoch": 0.00411373260738052,
+      "grad_norm": 4.318703651428223,
+      "learning_rate": 0.00018526401643540922,
+      "loss": 6.5227,
+      "step": 17
+    },
+    {
+      "epoch": 0.004355716878402904,
+      "grad_norm": 3.5019469261169434,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 6.579,
+      "step": 18
+    },
+    {
+      "epoch": 0.004597701149425287,
+      "grad_norm": 3.5339195728302,
+      "learning_rate": 0.0001760405965600031,
+      "loss": 6.0713,
+      "step": 19
+    },
+    {
+      "epoch": 0.004839685420447671,
+      "grad_norm": 3.601715564727783,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 6.1731,
+      "step": 20
+    },
+    {
+      "epoch": 0.005081669691470054,
+      "grad_norm": 3.8356359004974365,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 5.7358,
+      "step": 21
+    },
+    {
+      "epoch": 0.005323653962492438,
+      "grad_norm": 3.1003851890563965,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 5.5531,
+      "step": 22
+    },
+    {
+      "epoch": 0.0055656382335148216,
+      "grad_norm": 2.5003840923309326,
+      "learning_rate": 0.0001522498564715949,
+      "loss": 4.4929,
+      "step": 23
+    },
+    {
+      "epoch": 0.005807622504537205,
+      "grad_norm": 3.624629259109497,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 5.5564,
+      "step": 24
+    },
+    {
+      "epoch": 0.006049606775559589,
+      "grad_norm": 3.041182041168213,
+      "learning_rate": 0.000138268343236509,
+      "loss": 5.2167,
+      "step": 25
+    },
+    {
+      "epoch": 0.006291591046581972,
+      "grad_norm": 3.689633846282959,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.2159,
+      "step": 26
+    },
+    {
+      "epoch": 0.006291591046581972,
+      "eval_loss": 1.4802727699279785,
+      "eval_runtime": 34.6152,
+      "eval_samples_per_second": 50.267,
+      "eval_steps_per_second": 25.133,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 515037336698880.0,
+  "total_flos": 1007681745715200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null