Training in progress, step 756
Browse files
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 87368144
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:295773f289459b3ff450381bf3a62ff6413b8da6181c5c678ce72a9d6eeb3ce2
|
| 3 |
size 87368144
|
logging.jsonl
CHANGED
|
@@ -88,3 +88,7 @@
|
|
| 88 |
{"loss": 0.59742956, "grad_norm": 0.46738109, "learning_rate": 6.2e-07, "token_acc": 0.81762888, "epoch": 2.85948769, "global_step/max_steps": "720/756", "percentage": "95.24%", "elapsed_time": "4h 55m 31s", "remaining_time": "14m 46s", "memory(GiB)": 31.68, "train_speed(iter/s)": 0.040605}
|
| 89 |
{"loss": 0.61027303, "grad_norm": 0.47740796, "learning_rate": 3.2e-07, "token_acc": 0.81291669, "epoch": 2.89927879, "global_step/max_steps": "730/756", "percentage": "96.56%", "elapsed_time": "4h 59m 17s", "remaining_time": "10m 39s", "memory(GiB)": 31.68, "train_speed(iter/s)": 0.040652}
|
| 90 |
{"loss": 0.60262928, "grad_norm": 0.39351776, "learning_rate": 1.2e-07, "token_acc": 0.81533332, "epoch": 2.93906988, "global_step/max_steps": "740/756", "percentage": "97.88%", "elapsed_time": "5h 2m 56s", "remaining_time": "6m 33s", "memory(GiB)": 31.68, "train_speed(iter/s)": 0.040711}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
{"loss": 0.59742956, "grad_norm": 0.46738109, "learning_rate": 6.2e-07, "token_acc": 0.81762888, "epoch": 2.85948769, "global_step/max_steps": "720/756", "percentage": "95.24%", "elapsed_time": "4h 55m 31s", "remaining_time": "14m 46s", "memory(GiB)": 31.68, "train_speed(iter/s)": 0.040605}
|
| 89 |
{"loss": 0.61027303, "grad_norm": 0.47740796, "learning_rate": 3.2e-07, "token_acc": 0.81291669, "epoch": 2.89927879, "global_step/max_steps": "730/756", "percentage": "96.56%", "elapsed_time": "4h 59m 17s", "remaining_time": "10m 39s", "memory(GiB)": 31.68, "train_speed(iter/s)": 0.040652}
|
| 90 |
{"loss": 0.60262928, "grad_norm": 0.39351776, "learning_rate": 1.2e-07, "token_acc": 0.81533332, "epoch": 2.93906988, "global_step/max_steps": "740/756", "percentage": "97.88%", "elapsed_time": "5h 2m 56s", "remaining_time": "6m 33s", "memory(GiB)": 31.68, "train_speed(iter/s)": 0.040711}
|
| 91 |
+
{"loss": 0.60620799, "grad_norm": 0.43030033, "learning_rate": 2e-08, "token_acc": 0.81408437, "epoch": 2.97886098, "global_step/max_steps": "750/756", "percentage": "99.21%", "elapsed_time": "5h 6m 43s", "remaining_time": "2m 27s", "memory(GiB)": 31.68, "train_speed(iter/s)": 0.040754}
|
| 92 |
+
{"eval_loss": 2.43168187, "eval_runtime": 81.8657, "eval_samples_per_second": 2.235, "eval_steps_per_second": 0.562, "eval_token_acc": 0.81765685, "epoch": 2.97886098, "global_step/max_steps": "750/756", "percentage": "99.21%", "elapsed_time": "5h 8m 5s", "remaining_time": "2m 27s", "memory(GiB)": 31.68, "train_speed(iter/s)": 0.040573}
|
| 93 |
+
{"eval_loss": 2.43212795, "eval_runtime": 81.3299, "eval_samples_per_second": 2.25, "eval_steps_per_second": 0.566, "eval_token_acc": 0.81747906, "epoch": 3.0, "global_step/max_steps": "756/756", "percentage": "100.00%", "elapsed_time": "5h 11m 27s", "remaining_time": "0s", "memory(GiB)": 31.68, "train_speed(iter/s)": 0.040455}
|
| 94 |
+
{"train_runtime": 18692.3405, "train_samples_per_second": 0.645, "train_steps_per_second": 0.04, "total_flos": 3.421626729187456e+19, "train_loss": 0.66581451, "epoch": 3.0, "global_step/max_steps": "756/756", "percentage": "100.00%", "elapsed_time": "5h 11m 29s", "remaining_time": "0s", "memory(GiB)": 31.68, "train_speed(iter/s)": 0.040451}
|
runs/events.out.tfevents.1770820661.h004.gautschi.rcac.purdue.edu.2476766.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66676f464c8f6c7520d2e3b991cfddd05edb1e2f58e599ce148b28b2f722e055
|
| 3 |
+
size 33504
|