Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:538cabf0b0c92a5e8570a9c3c53f42b9cd71b3c827f55f61687ade9f40d48373
+oid sha256:d82e8e0e0dcc9d2998e249d1fefe90fca6ab46f7b4194ac92aabc16d3b28dde8
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:002484a5c03baaedb10c2a63b37b2032032ff9cb36c54660ac399246045eb621
+oid sha256:2ba42073890b1b448d8efb6df10e79dcb9a2614f7dffd68d44dfea04e8b249b0
 size 1054135994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2616293446c1c2f2c6b0e270c4bb50dd25782b075145433b30550e3bb3a1845c
+oid sha256:afdcd158786234085082ce38b1824c51dd8c72881220443fc2d1c6f4e031a983
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da0b9a1e2fa3da24e9af8b74787d70ff4c95d9bc9b74eeab135df0350a00b462
+oid sha256:8cf3f988e8fed2daa2e801eb1f19b681872781cf57f0fb7b896e859a12cfe2bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,351 +1,125 @@
 {
-  "best_metric": 0.7166298031806946,
-  "best_model_checkpoint": "./output/checkpoint-450",
-  "epoch": 19.565217391304348,
+  "best_metric": 0.7955127954483032,
+  "best_model_checkpoint": "./output/checkpoint-150",
+  "epoch": 6.521739130434782,
   "eval_steps": 150,
-  "global_step": 450,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.43478260869565216,
-      "grad_norm": 1.502166986465454,
+      "grad_norm": 1.5021542310714722,
       "learning_rate": 3e-06,
       "loss": 0.9062,
       "step": 10
     },
     {
       "epoch": 0.8695652173913043,
-      "grad_norm": 1.687074065208435,
+      "grad_norm": 1.6870979070663452,
       "learning_rate": 6e-06,
-      "loss": 0.9026,
+      "loss": 0.9027,
       "step": 20
     },
     {
       "epoch": 1.3043478260869565,
-      "grad_norm": 1.7296172380447388,
+      "grad_norm": 1.729711651802063,
       "learning_rate": 9e-06,
       "loss": 0.9002,
       "step": 30
     },
     {
       "epoch": 1.7391304347826086,
-      "grad_norm": 1.4458578824996948,
+      "grad_norm": 1.4458218812942505,
       "learning_rate": 1.2e-05,
       "loss": 0.9088,
       "step": 40
     },
     {
       "epoch": 2.1739130434782608,
-      "grad_norm": 1.3517787456512451,
+      "grad_norm": 1.3517591953277588,
       "learning_rate": 1.5e-05,
-      "loss": 0.8361,
+      "loss": 0.8359,
       "step": 50
     },
     {
       "epoch": 2.608695652173913,
-      "grad_norm": 2.0466721057891846,
+      "grad_norm": 2.046574115753174,
       "learning_rate": 1.8e-05,
-      "loss": 0.8895,
+      "loss": 0.8892,
       "step": 60
     },
     {
       "epoch": 3.0434782608695654,
-      "grad_norm": 1.4843413829803467,
+      "grad_norm": 1.491979956626892,
       "learning_rate": 2.1e-05,
-      "loss": 0.8915,
+      "loss": 0.8914,
       "step": 70
     },
     {
       "epoch": 3.4782608695652173,
-      "grad_norm": 1.7294325828552246,
+      "grad_norm": 1.7294977903366089,
       "learning_rate": 2.4e-05,
-      "loss": 0.8233,
+      "loss": 0.8235,
       "step": 80
     },
     {
       "epoch": 3.9130434782608696,
-      "grad_norm": 1.424039602279663,
+      "grad_norm": 1.424176812171936,
       "learning_rate": 2.7000000000000002e-05,
       "loss": 0.8528,
       "step": 90
     },
     {
       "epoch": 4.3478260869565215,
-      "grad_norm": 1.3659141063690186,
+      "grad_norm": 1.3658121824264526,
       "learning_rate": 3e-05,
-      "loss": 0.8647,
+      "loss": 0.8646,
       "step": 100
     },
     {
       "epoch": 4.782608695652174,
-      "grad_norm": 2.1984479427337646,
+      "grad_norm": 2.1974833011627197,
       "learning_rate": 2.999999702723963e-05,
-      "loss": 0.8224,
+      "loss": 0.8226,
       "step": 110
     },
     {
       "epoch": 5.217391304347826,
-      "grad_norm": 1.0726439952850342,
+      "grad_norm": 1.0727229118347168,
       "learning_rate": 2.9999988108959687e-05,
-      "loss": 0.7649,
+      "loss": 0.7652,
       "step": 120
     },
     {
       "epoch": 5.6521739130434785,
-      "grad_norm": 1.5597559213638306,
+      "grad_norm": 1.5599604845046997,
       "learning_rate": 2.9999973245163716e-05,
       "loss": 0.7412,
       "step": 130
     },
     {
       "epoch": 6.086956521739131,
-      "grad_norm": 1.9070907831192017,
+      "grad_norm": 1.907434105873108,
       "learning_rate": 2.99999524358576e-05,
-      "loss": 0.7652,
+      "loss": 0.7657,
       "step": 140
     },
     {
       "epoch": 6.521739130434782,
-      "grad_norm": 1.1221362352371216,
+      "grad_norm": 1.1226494312286377,
       "learning_rate": 2.9999925681049593e-05,
-      "loss": 0.7857,
+      "loss": 0.7858,
       "step": 150
     },
     {
       "epoch": 6.521739130434782,
-      "eval_loss": 0.7971361875534058,
-      "eval_runtime": 0.4925,
-      "eval_samples_per_second": 20.305,
-      "eval_steps_per_second": 20.305,
+      "eval_loss": 0.7955127954483032,
+      "eval_runtime": 0.4729,
+      "eval_samples_per_second": 21.146,
+      "eval_steps_per_second": 21.146,
       "step": 150
-    },
-    {
-      "epoch": 6.956521739130435,
-      "grad_norm": 1.5332696437835693,
-      "learning_rate": 2.9999892980750297e-05,
-      "loss": 0.6584,
-      "step": 160
-    },
-    {
-      "epoch": 7.391304347826087,
-      "grad_norm": 1.3473052978515625,
-      "learning_rate": 2.9999854334972675e-05,
-      "loss": 0.7387,
-      "step": 170
-    },
-    {
-      "epoch": 7.826086956521739,
-      "grad_norm": 1.7264468669891357,
-      "learning_rate": 2.999980974373204e-05,
-      "loss": 0.7291,
-      "step": 180
-    },
-    {
-      "epoch": 8.26086956521739,
-      "grad_norm": 1.5402302742004395,
-      "learning_rate": 2.9999759207046075e-05,
-      "loss": 0.6245,
-      "step": 190
-    },
-    {
-      "epoch": 8.695652173913043,
-      "grad_norm": 1.7418005466461182,
-      "learning_rate": 2.9999702724934804e-05,
-      "loss": 0.6762,
-      "step": 200
-    },
-    {
-      "epoch": 9.130434782608695,
-      "grad_norm": 1.0412225723266602,
-      "learning_rate": 2.999964029742062e-05,
-      "loss": 0.6522,
-      "step": 210
-    },
-    {
-      "epoch": 9.565217391304348,
-      "grad_norm": 1.21176016330719,
-      "learning_rate": 2.9999571924528263e-05,
-      "loss": 0.559,
-      "step": 220
-    },
-    {
-      "epoch": 10.0,
-      "grad_norm": 1.5270979404449463,
-      "learning_rate": 2.9999497606284837e-05,
-      "loss": 0.7554,
-      "step": 230
-    },
-    {
-      "epoch": 10.434782608695652,
-      "grad_norm": 1.421043038368225,
-      "learning_rate": 2.9999417342719796e-05,
-      "loss": 0.712,
-      "step": 240
-    },
-    {
-      "epoch": 10.869565217391305,
-      "grad_norm": 0.975618839263916,
-      "learning_rate": 2.9999331133864956e-05,
-      "loss": 0.5897,
-      "step": 250
-    },
-    {
-      "epoch": 11.304347826086957,
-      "grad_norm": 1.1942723989486694,
-      "learning_rate": 2.9999238979754485e-05,
-      "loss": 0.6545,
-      "step": 260
-    },
-    {
-      "epoch": 11.73913043478261,
-      "grad_norm": 1.0494939088821411,
-      "learning_rate": 2.999914088042492e-05,
-      "loss": 0.6475,
-      "step": 270
-    },
-    {
-      "epoch": 12.173913043478262,
-      "grad_norm": 1.31776762008667,
-      "learning_rate": 2.9999036835915132e-05,
-      "loss": 0.594,
-      "step": 280
-    },
-    {
-      "epoch": 12.608695652173914,
-      "grad_norm": 1.0847584009170532,
-      "learning_rate": 2.9998926846266365e-05,
-      "loss": 0.6326,
-      "step": 290
-    },
-    {
-      "epoch": 13.043478260869565,
-      "grad_norm": 1.3872359991073608,
-      "learning_rate": 2.9998810911522213e-05,
-      "loss": 0.5809,
-      "step": 300
-    },
-    {
-      "epoch": 13.043478260869565,
-      "eval_loss": 0.7315621376037598,
-      "eval_runtime": 0.476,
-      "eval_samples_per_second": 21.009,
-      "eval_steps_per_second": 21.009,
-      "step": 300
-    },
-    {
-      "epoch": 13.478260869565217,
-      "grad_norm": 1.7903343439102173,
-      "learning_rate": 2.9998689031728636e-05,
-      "loss": 0.5144,
-      "step": 310
-    },
-    {
-      "epoch": 13.91304347826087,
-      "grad_norm": 1.5240825414657593,
-      "learning_rate": 2.9998561206933938e-05,
-      "loss": 0.6496,
-      "step": 320
-    },
-    {
-      "epoch": 14.347826086956522,
-      "grad_norm": 1.4871171712875366,
-      "learning_rate": 2.9998427437188786e-05,
-      "loss": 0.5741,
-      "step": 330
-    },
-    {
-      "epoch": 14.782608695652174,
-      "grad_norm": 1.3173134326934814,
-      "learning_rate": 2.99982877225462e-05,
-      "loss": 0.6017,
-      "step": 340
-    },
-    {
-      "epoch": 15.217391304347826,
-      "grad_norm": 0.978571355342865,
-      "learning_rate": 2.9998142063061564e-05,
-      "loss": 0.4988,
-      "step": 350
-    },
-    {
-      "epoch": 15.652173913043478,
-      "grad_norm": 1.6439123153686523,
-      "learning_rate": 2.9997990458792603e-05,
-      "loss": 0.5627,
-      "step": 360
-    },
-    {
-      "epoch": 16.08695652173913,
-      "grad_norm": 1.6352148056030273,
-      "learning_rate": 2.9997832909799417e-05,
-      "loss": 0.6671,
-      "step": 370
-    },
-    {
-      "epoch": 16.52173913043478,
-      "grad_norm": 0.9533625245094299,
-      "learning_rate": 2.9997669416144452e-05,
-      "loss": 0.5128,
-      "step": 380
-    },
-    {
-      "epoch": 16.956521739130434,
-      "grad_norm": 0.9373893737792969,
-      "learning_rate": 2.999749997789251e-05,
-      "loss": 0.5796,
-      "step": 390
-    },
-    {
-      "epoch": 17.391304347826086,
-      "grad_norm": 1.1115307807922363,
-      "learning_rate": 2.9997324595110743e-05,
-      "loss": 0.518,
-      "step": 400
-    },
-    {
-      "epoch": 17.82608695652174,
-      "grad_norm": 1.2844030857086182,
-      "learning_rate": 2.9997143267868683e-05,
-      "loss": 0.5877,
-      "step": 410
-    },
-    {
-      "epoch": 18.26086956521739,
-      "grad_norm": 1.1645976305007935,
-      "learning_rate": 2.9996955996238192e-05,
-      "loss": 0.5059,
-      "step": 420
-    },
-    {
-      "epoch": 18.695652173913043,
-      "grad_norm": 1.1995220184326172,
-      "learning_rate": 2.9996762780293503e-05,
-      "loss": 0.5316,
-      "step": 430
-    },
-    {
-      "epoch": 19.130434782608695,
-      "grad_norm": 1.2067248821258545,
-      "learning_rate": 2.9996563620111197e-05,
-      "loss": 0.5334,
-      "step": 440
-    },
-    {
-      "epoch": 19.565217391304348,
-      "grad_norm": 1.424436330795288,
-      "learning_rate": 2.9996358515770218e-05,
-      "loss": 0.5677,
-      "step": 450
-    },
-    {
-      "epoch": 19.565217391304348,
-      "eval_loss": 0.7166298031806946,
-      "eval_runtime": 0.4027,
-      "eval_samples_per_second": 24.83,
-      "eval_steps_per_second": 24.83,
-      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -365,7 +139,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1591800814075904e+16,
+  "total_flos": 3894839614291968.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6df4c7bb743e4dde6c0012813954641954f96e025235aaf027e7b00df2c6d40
+oid sha256:ee692113fb2c89dec15bfcbf8b44e5a56ed22100c62a6e9410f5bd2dc526efaa
 size 5368