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:fec89d57ceae0a0ee03cfb2a234aa95bb774eb0120d072aafd545a4b4d592741
+oid sha256:8c8c462fb6139f0e5e94a428c17151389a00ddf98776a8d929a9e84fa7429f11
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c426c526b9529c0763f2c622c43b3a5e7c47d79aaf63768327bb3a88a397fb89
+oid sha256:880b9e1dfe48deb1551eafee43c61c4b587a4b50183f3f4c5584e59044f157db
 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": 10.3441,
       "step": 75
+    },
+    {
+      "epoch": 2.3384615384615386,
+      "grad_norm": 0.6675054430961609,
+      "learning_rate": 1.3700225403843469e-05,
+      "loss": 10.3299,
+      "step": 76
+    },
+    {
+      "epoch": 2.3692307692307693,
+      "grad_norm": 0.5850571990013123,
+      "learning_rate": 1.2482508892179884e-05,
+      "loss": 10.3144,
+      "step": 77
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.6561471223831177,
+      "learning_rate": 1.1313708031358183e-05,
+      "loss": 10.3181,
+      "step": 78
+    },
+    {
+      "epoch": 2.430769230769231,
+      "grad_norm": 0.6304017305374146,
+      "learning_rate": 1.0195346714717813e-05,
+      "loss": 10.3316,
+      "step": 79
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 0.627305269241333,
+      "learning_rate": 9.12888307205541e-06,
+      "loss": 10.321,
+      "step": 80
+    },
+    {
+      "epoch": 2.4923076923076923,
+      "grad_norm": 0.6237972974777222,
+      "learning_rate": 8.115707568501768e-06,
+      "loss": 10.3571,
+      "step": 81
+    },
+    {
+      "epoch": 2.4923076923076923,
+      "eval_loss": 10.326565742492676,
+      "eval_runtime": 0.0741,
+      "eval_samples_per_second": 1471.008,
+      "eval_steps_per_second": 53.982,
+      "step": 81
+    },
+    {
+      "epoch": 2.523076923076923,
+      "grad_norm": 0.627188503742218,
+      "learning_rate": 7.157141191620548e-06,
+      "loss": 10.3486,
+      "step": 82
+    },
+    {
+      "epoch": 2.5538461538461537,
+      "grad_norm": 0.63338303565979,
+      "learning_rate": 6.2544337290925185e-06,
+      "loss": 10.3175,
+      "step": 83
+    },
+    {
+      "epoch": 2.5846153846153848,
+      "grad_norm": 0.5604279041290283,
+      "learning_rate": 5.408762139230888e-06,
+      "loss": 10.3171,
+      "step": 84
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 0.6100577712059021,
+      "learning_rate": 4.621229016452156e-06,
+      "loss": 10.3251,
+      "step": 85
+    },
+    {
+      "epoch": 2.646153846153846,
+      "grad_norm": 0.6354370713233948,
+      "learning_rate": 3.892861153703342e-06,
+      "loss": 10.3134,
+      "step": 86
+    },
+    {
+      "epoch": 2.676923076923077,
+      "grad_norm": 0.6003406643867493,
+      "learning_rate": 3.2246082037199532e-06,
+      "loss": 10.3045,
+      "step": 87
+    },
+    {
+      "epoch": 2.707692307692308,
+      "grad_norm": 0.5505728125572205,
+      "learning_rate": 2.6173414408598827e-06,
+      "loss": 10.3232,
+      "step": 88
+    },
+    {
+      "epoch": 2.7384615384615385,
+      "grad_norm": 0.6088215708732605,
+      "learning_rate": 2.0718526251279346e-06,
+      "loss": 10.3132,
+      "step": 89
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 0.6168414950370789,
+      "learning_rate": 1.5888529698718346e-06,
+      "loss": 10.3199,
+      "step": 90
+    },
+    {
+      "epoch": 2.769230769230769,
+      "eval_loss": 10.325533866882324,
+      "eval_runtime": 0.0753,
+      "eval_samples_per_second": 1447.667,
+      "eval_steps_per_second": 53.125,
+      "step": 90
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.6565277576446533,
+      "learning_rate": 1.1689722144956671e-06,
+      "loss": 10.3263,
+      "step": 91
+    },
+    {
+      "epoch": 2.830769230769231,
+      "grad_norm": 0.7084165811538696,
+      "learning_rate": 8.127578033998662e-07,
+      "loss": 10.3452,
+      "step": 92
+    },
+    {
+      "epoch": 2.8615384615384616,
+      "grad_norm": 0.5756314396858215,
+      "learning_rate": 5.206741722181386e-07,
+      "loss": 10.319,
+      "step": 93
+    },
+    {
+      "epoch": 2.8923076923076922,
+      "grad_norm": 0.5791900753974915,
+      "learning_rate": 2.9310214228202013e-07,
+      "loss": 10.308,
+      "step": 94
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 0.6099293828010559,
+      "learning_rate": 1.3033842410251075e-07,
+      "loss": 10.315,
+      "step": 95
+    },
+    {
+      "epoch": 2.953846153846154,
+      "grad_norm": 0.5944267511367798,
+      "learning_rate": 3.259523051615254e-08,
+      "loss": 10.3374,
+      "step": 96
+    },
+    {
+      "epoch": 2.9846153846153847,
+      "grad_norm": 0.618131160736084,
+      "learning_rate": 0.0,
+      "loss": 10.3129,
+      "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