Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d264dda68f41fba6eb5dba9a585a510fb9b3d753af81ccec1015005947682235
+oid sha256:fec89d57ceae0a0ee03cfb2a234aa95bb774eb0120d072aafd545a4b4d592741
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1083c750e495b6e6fdab421e66291d4f82cfaa07d10da4f4215fc8d6b1871154
+oid sha256:c426c526b9529c0763f2c622c43b3a5e7c47d79aaf63768327bb3a88a397fb89
 size 118090

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f699f010db684a3c9930ab741407256ee8eccb1f91864778668a998661bf53e
+oid sha256:6dcaeb8ce37dcd772f0be79409cf34a767b40d1a4aeff18fa4f28195e2557ee9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb9466cb0f4406b872db94f91c941ba4e6bd8b8f75768065c30577b6082e0df3
+oid sha256:5816b11415c5036548f2d19267172db3ec90908b671e4240ecc1a17b07b81f11
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91518c078cc87b6d72db505a715dee7376a7f9856a0e02bff458e4546a5c7ee1
+oid sha256:701d85fe6b3537bff4ef236e10ab7f64401dabbb0882efd052b0c54c0883d1a5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40ce070ec338db07ca72e7709c477efa484ca5e4bf94660875a08d69f708af27
+oid sha256:0ad1b00aaa5733663c30953876e4ea8b0beab56db59740bebd219ff25c93d957
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1a647e3cb9f019d66be656f671b0f6e626eada7227d358f0d941f9f9001a15e
+oid sha256:f222366b58c766825e43101b65c4879c55218b5ddfff387c45f2b7d7e2e0465e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.5384615384615383,
+  "epoch": 2.3076923076923075,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 5.6302485561014475e-05,
       "loss": 12.5208,
       "step": 50
+    },
+    {
+      "epoch": 1.5692307692307692,
+      "grad_norm": 0.43022680282592773,
+      "learning_rate": 5.4507654055603275e-05,
+      "loss": 9.2575,
+      "step": 51
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.38099291920661926,
+      "learning_rate": 5.270694542927088e-05,
+      "loss": 9.0721,
+      "step": 52
+    },
+    {
+      "epoch": 1.6307692307692307,
+      "grad_norm": 0.5643202662467957,
+      "learning_rate": 5.090270746252802e-05,
+      "loss": 11.2072,
+      "step": 53
+    },
+    {
+      "epoch": 1.6615384615384614,
+      "grad_norm": 0.4488671123981476,
+      "learning_rate": 4.909729253747197e-05,
+      "loss": 9.4193,
+      "step": 54
+    },
+    {
+      "epoch": 1.6615384615384614,
+      "eval_loss": 10.343835830688477,
+      "eval_runtime": 0.071,
+      "eval_samples_per_second": 1535.673,
+      "eval_steps_per_second": 56.355,
+      "step": 54
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 0.5811948776245117,
+      "learning_rate": 4.729305457072913e-05,
+      "loss": 11.7481,
+      "step": 55
+    },
+    {
+      "epoch": 1.7230769230769232,
+      "grad_norm": 0.41047021746635437,
+      "learning_rate": 4.549234594439674e-05,
+      "loss": 9.4589,
+      "step": 56
+    },
+    {
+      "epoch": 1.7538461538461538,
+      "grad_norm": 0.522146999835968,
+      "learning_rate": 4.3697514438985536e-05,
+      "loss": 11.107,
+      "step": 57
+    },
+    {
+      "epoch": 1.7846153846153845,
+      "grad_norm": 0.5175060629844666,
+      "learning_rate": 4.1910900172361764e-05,
+      "loss": 10.9767,
+      "step": 58
+    },
+    {
+      "epoch": 1.8153846153846154,
+      "grad_norm": 0.4755529463291168,
+      "learning_rate": 4.0134832548680006e-05,
+      "loss": 9.3121,
+      "step": 59
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 0.4807398021221161,
+      "learning_rate": 3.8371627221284495e-05,
+      "loss": 9.6356,
+      "step": 60
+    },
+    {
+      "epoch": 1.876923076923077,
+      "grad_norm": 0.5616713166236877,
+      "learning_rate": 3.6623583073538966e-05,
+      "loss": 10.963,
+      "step": 61
+    },
+    {
+      "epoch": 1.9076923076923076,
+      "grad_norm": 0.5250815153121948,
+      "learning_rate": 3.489297922152136e-05,
+      "loss": 10.1303,
+      "step": 62
+    },
+    {
+      "epoch": 1.9384615384615385,
+      "grad_norm": 0.6839239001274109,
+      "learning_rate": 3.3182072042491244e-05,
+      "loss": 11.6986,
+      "step": 63
+    },
+    {
+      "epoch": 1.9384615384615385,
+      "eval_loss": 10.335771560668945,
+      "eval_runtime": 0.0748,
+      "eval_samples_per_second": 1457.284,
+      "eval_steps_per_second": 53.478,
+      "step": 63
+    },
+    {
+      "epoch": 1.9692307692307693,
+      "grad_norm": 0.5417065620422363,
+      "learning_rate": 3.149309223300428e-05,
+      "loss": 9.5666,
+      "step": 64
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8907036185264587,
+      "learning_rate": 2.982824190050958e-05,
+      "loss": 15.1453,
+      "step": 65
+    },
+    {
+      "epoch": 2.0307692307692307,
+      "grad_norm": 0.5486352443695068,
+      "learning_rate": 2.8189691692221627e-05,
+      "loss": 10.3319,
+      "step": 66
+    },
+    {
+      "epoch": 2.0615384615384613,
+      "grad_norm": 0.5944435000419617,
+      "learning_rate": 2.65795779650105e-05,
+      "loss": 10.3267,
+      "step": 67
+    },
+    {
+      "epoch": 2.0923076923076924,
+      "grad_norm": 0.5956578254699707,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.313,
+      "step": 68
+    },
+    {
+      "epoch": 2.123076923076923,
+      "grad_norm": 0.592414379119873,
+      "learning_rate": 2.3453017265505673e-05,
+      "loss": 10.3379,
+      "step": 69
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 0.6250660419464111,
+      "learning_rate": 2.194064673188089e-05,
+      "loss": 10.3427,
+      "step": 70
+    },
+    {
+      "epoch": 2.184615384615385,
+      "grad_norm": 0.6292226910591125,
+      "learning_rate": 2.0464860241772455e-05,
+      "loss": 10.3298,
+      "step": 71
+    },
+    {
+      "epoch": 2.2153846153846155,
+      "grad_norm": 0.5584103465080261,
+      "learning_rate": 1.902758193921385e-05,
+      "loss": 10.3342,
+      "step": 72
+    },
+    {
+      "epoch": 2.2153846153846155,
+      "eval_loss": 10.32968807220459,
+      "eval_runtime": 0.0724,
+      "eval_samples_per_second": 1505.761,
+      "eval_steps_per_second": 55.257,
+      "step": 72
+    },
+    {
+      "epoch": 2.246153846153846,
+      "grad_norm": 0.5744684934616089,
+      "learning_rate": 1.7630685760908622e-05,
+      "loss": 10.3275,
+      "step": 73
+    },
+    {
+      "epoch": 2.276923076923077,
+      "grad_norm": 0.6510607600212097,
+      "learning_rate": 1.6275992992974308e-05,
+      "loss": 10.3399,
+      "step": 74
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 0.6014554500579834,
+      "learning_rate": 1.4965269896332885e-05,
+      "loss": 10.3441,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 10460489318400.0,
+  "total_flos": 15690733977600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null