Training in progress, step 97, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a161797bcad6ee955baf6b2ad6f45b43a3cb2a8a885457fd3ab16a59dc102405
+oid sha256:debbb7fe888120c0d83c8f02a79e7aa25de49fba5efeb6c1bc175b3eb5f63416
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cc3b71b37f6dfa57b025ed570c00b7fe05135366ce08bd0650de4a15dc6e0e1
+oid sha256:2a8aff59007ed4451e58311d5f0b822ac7c7d0d2cf57a4d141060f4c83ae462a
 size 118090

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dcaeb8ce37dcd772f0be79409cf34a767b40d1a4aeff18fa4f28195e2557ee9
+oid sha256:c2a57261bcc318db0caad0e14f10cd5b62e6dad037e9a33455ef57c76b2c8755
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5816b11415c5036548f2d19267172db3ec90908b671e4240ecc1a17b07b81f11
+oid sha256:c5a0f9ca32dd7355eff9a8526368871477011022c0c3d73bb9ae842a19e06bd9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:701d85fe6b3537bff4ef236e10ab7f64401dabbb0882efd052b0c54c0883d1a5
+oid sha256:9d641a52eb7c5b99c4c0f231d3cdfdc26601b34efcbb2b98c01048de34abe2bb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ad1b00aaa5733663c30953876e4ea8b0beab56db59740bebd219ff25c93d957
+oid sha256:318f8dc9629230dc31c2206338dd42de78cf943c3f0a30587606c753ad393775
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f222366b58c766825e43101b65c4879c55218b5ddfff387c45f2b7d7e2e0465e
+oid sha256:6145c7e827928ce363c3dece9b28ea4d59912ec6339b2dd62ab9cd74a51e4307
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.3076923076923075,
+  "epoch": 2.9846153846153847,
   "eval_steps": 9,
-  "global_step": 75,
+  "global_step": 97,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -604,6 +604,176 @@
       "learning_rate": 1.4965269896332885e-05,
       "loss": 10.357,
       "step": 75
+    },
+    {
+      "epoch": 2.3384615384615386,
+      "grad_norm": 0.43965718150138855,
+      "learning_rate": 1.3700225403843469e-05,
+      "loss": 10.3463,
+      "step": 76
+    },
+    {
+      "epoch": 2.3692307692307693,
+      "grad_norm": 0.4108678102493286,
+      "learning_rate": 1.2482508892179884e-05,
+      "loss": 10.3279,
+      "step": 77
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.4643837809562683,
+      "learning_rate": 1.1313708031358183e-05,
+      "loss": 10.3312,
+      "step": 78
+    },
+    {
+      "epoch": 2.430769230769231,
+      "grad_norm": 0.41802978515625,
+      "learning_rate": 1.0195346714717813e-05,
+      "loss": 10.3462,
+      "step": 79
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 0.4295816719532013,
+      "learning_rate": 9.12888307205541e-06,
+      "loss": 10.335,
+      "step": 80
+    },
+    {
+      "epoch": 2.4923076923076923,
+      "grad_norm": 0.4365237057209015,
+      "learning_rate": 8.115707568501768e-06,
+      "loss": 10.3688,
+      "step": 81
+    },
+    {
+      "epoch": 2.4923076923076923,
+      "eval_loss": 10.340795516967773,
+      "eval_runtime": 0.0704,
+      "eval_samples_per_second": 1548.395,
+      "eval_steps_per_second": 56.822,
+      "step": 81
+    },
+    {
+      "epoch": 2.523076923076923,
+      "grad_norm": 0.4135013818740845,
+      "learning_rate": 7.157141191620548e-06,
+      "loss": 10.3619,
+      "step": 82
+    },
+    {
+      "epoch": 2.5538461538461537,
+      "grad_norm": 0.4040301740169525,
+      "learning_rate": 6.2544337290925185e-06,
+      "loss": 10.3343,
+      "step": 83
+    },
+    {
+      "epoch": 2.5846153846153848,
+      "grad_norm": 0.42589643597602844,
+      "learning_rate": 5.408762139230888e-06,
+      "loss": 10.3278,
+      "step": 84
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 0.39326804876327515,
+      "learning_rate": 4.621229016452156e-06,
+      "loss": 10.3402,
+      "step": 85
+    },
+    {
+      "epoch": 2.646153846153846,
+      "grad_norm": 0.4585588276386261,
+      "learning_rate": 3.892861153703342e-06,
+      "loss": 10.3275,
+      "step": 86
+    },
+    {
+      "epoch": 2.676923076923077,
+      "grad_norm": 0.40692827105522156,
+      "learning_rate": 3.2246082037199532e-06,
+      "loss": 10.3185,
+      "step": 87
+    },
+    {
+      "epoch": 2.707692307692308,
+      "grad_norm": 0.3903280794620514,
+      "learning_rate": 2.6173414408598827e-06,
+      "loss": 10.3358,
+      "step": 88
+    },
+    {
+      "epoch": 2.7384615384615385,
+      "grad_norm": 0.4182497262954712,
+      "learning_rate": 2.0718526251279346e-06,
+      "loss": 10.3275,
+      "step": 89
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 0.42589595913887024,
+      "learning_rate": 1.5888529698718346e-06,
+      "loss": 10.3345,
+      "step": 90
+    },
+    {
+      "epoch": 2.769230769230769,
+      "eval_loss": 10.339981079101562,
+      "eval_runtime": 0.0715,
+      "eval_samples_per_second": 1524.932,
+      "eval_steps_per_second": 55.961,
+      "step": 90
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.451843798160553,
+      "learning_rate": 1.1689722144956671e-06,
+      "loss": 10.3391,
+      "step": 91
+    },
+    {
+      "epoch": 2.830769230769231,
+      "grad_norm": 0.4803301692008972,
+      "learning_rate": 8.127578033998662e-07,
+      "loss": 10.3616,
+      "step": 92
+    },
+    {
+      "epoch": 2.8615384615384616,
+      "grad_norm": 0.42532211542129517,
+      "learning_rate": 5.206741722181386e-07,
+      "loss": 10.3314,
+      "step": 93
+    },
+    {
+      "epoch": 2.8923076923076922,
+      "grad_norm": 0.43129971623420715,
+      "learning_rate": 2.9310214228202013e-07,
+      "loss": 10.3205,
+      "step": 94
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 0.43747344613075256,
+      "learning_rate": 1.3033842410251075e-07,
+      "loss": 10.3268,
+      "step": 95
+    },
+    {
+      "epoch": 2.953846153846154,
+      "grad_norm": 0.4085710346698761,
+      "learning_rate": 3.259523051615254e-08,
+      "loss": 10.3505,
+      "step": 96
+    },
+    {
+      "epoch": 2.9846153846153847,
+      "grad_norm": 0.43386417627334595,
+      "learning_rate": 0.0,
+      "loss": 10.326,
+      "step": 97
     }
   ],
   "logging_steps": 1,
@@ -618,12 +788,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 15690733977600.0,
+  "total_flos": 20293349277696.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null